Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 376 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0263. Min Act: -0.0006

Data Index: 1240040 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0259. Min Act: -0.0006

Data Index: 1220572 (C4 (Web Text))

Max Activating Token Index: 694

Text #2

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0251. Min Act: -0.0006

Data Index: 62560 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0246. Min Act: -0.0006

Data Index: 4187 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0255. Min Act: -0.0006

Data Index: 1023127 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0245. Min Act: -0.0006

Data Index: 952161 (C4 (Web Text))

Max Activating Token Index: 847

Text #6

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0241. Min Act: -0.0006

Data Index: 133543 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0234. Min Act: -0.0006

Data Index: 586193 (C4 (Web Text))

Max Activating Token Index: 345

Text #8

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0238. Min Act: -0.0006

Data Index: 869702 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0236. Min Act: -0.0006

Data Index: 949759 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0236. Min Act: -0.0006

Data Index: 219253 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0235. Min Act: -0.0006

Data Index: 1224499 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0234. Min Act: -0.0006

Data Index: 1346632 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0233. Min Act: -0.0006

Data Index: 87283 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0230. Min Act: -0.0006

Data Index: 115368 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0224. Min Act: -0.0006

Data Index: 1300566 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0229. Min Act: -0.0006

Data Index: 712445 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0227. Min Act: -0.0006

Data Index: 748315 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0227. Min Act: -0.0006

Data Index: 308100 (C4 (Web Text))

Max Activating Token Index: 765

Text #19

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0227. Min Act: -0.0006

Data Index: 655145 (C4 (Web Text))

Max Activating Token Index: 363