Produced as part of the SERI ML Alignment Theory Scholars Program - Winter 2022 Cohort.

What if I told you that in just one weekend you can get up to speed doing practical Mechanistic Interpretability research on Transformers? Surprised? Then this is your tutorial!

I'll give you a view to how I research Transformer circuits in practice, show you the tools you need, and explain my thought process along the way. I focus on the practical side to get started with interventions; for more background see point 2 below.

Prerequisites:

Understanding the Transformer architecture: Know what the residual stream is, how attention layers and MLPs work, and how logits & predictions work. For future sections familiarity with multi-head attention is useful. Here’s a link to Neel’s glossary which provides excellent explanations for most terms I might use!
If you're not familiar with Transformers you can check out Step 2 (6) on Neel's guide or any of the other explanations online, I recommend Jay Alammar's The Illustrated Transformer and/or Milan Straka's lecture series.
Some overview of Mechanistic Interpretability is helpful: See e.g. any of Neel's talks, or look at the results in the IOI paper / walkthrough.
Basic Python: Familiarity with arrays (as in NumPy or PyTorch, for indices) is useful; but explicitly no PyTorch knowledge required!

No hardware required, free Google Colab account works fine for this. Here's a notebook with all the code from this tutorial! PS: Here's a little web page where you can run some of these methods online! No trivial inconveniences!

Step 0: Setup

Open a notebook (e.g. Colab) and install Neel Nanda’s TransformerLens (formerly known as EasyTransformer).

!pip install transformer_lens

Step 1: Getting a model to play with

from transformer_lens import HookedTransformer, utils
model = HookedTransformer.from_pretrained("gpt2-small")

That’s it, now you’ve got a GPT2 model to play with! TransformerLens supports most relevant open source transformers. Here’s how to run the language model

logits = model("Famous computer scientist Alan")
# The logit dimensions are: [batch, position, vocab]
next_token_logits = logits[0, -1]
next_token_prediction = next_token_logits.argmax()
next_word_prediction = model.tokenizer.decode(next_token_prediction)
print(next_word_prediction)

Let’s have a look at the intern...

geonhee kim

geonhee kim

geonhee kim

geonhee kim

geonhee kim

geonhee kim