Visualizing every token and memory copy in transformer ops from 2 years of experiments

ctjlewis · x · 2026-09-28

ctjlewis showcases a visualization of transformer internals that reveals the exact tokens written, color-coding each slot in the operation and tracing how information flows from previous tokens to the next one. Solid fills mark computed values; bordered slots are copy operations reading prior values from tape-memory.

The work will cover two years of computational experiments across several generations of models, and the author argues it beats 99% of academic literature, which he says is largely complaints about what models supposedly cannot do.

Related event: Visualizing Claude Opus 4.6's Internal Multiplication: Two Years of Experiments Become a Paper(6 posts)→

Original post →

More from Research

Research channel →