Given a computer that can handle the representation and convert it into form acceptable by the interface of your mind, this data can be converted into a high-level description. The data determines its high-level properties, even if you are unable to extract them, just like a given number determines which prime factors it has, even if you are unable to factor it.
I happen to agree. However, the claim of reductionism is that what you've described is the case for ALL entities. I'm trying to figure out why this claim is logically necessary, and any disagreement is a confusion.
Here's our place to discuss Less Wrong topics that have not appeared in recent posts. Have fun building smaller brains inside of your brains (or not, as you please).