Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2304 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0280. Min Act: -0.0003

Data Index: 387551 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0260. Min Act: -0.0003

Data Index: 754202 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0281. Min Act: -0.0003

Data Index: 729679 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0256. Min Act: -0.0003

Data Index: 485810 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0250. Min Act: -0.0003

Data Index: 1210589 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0244. Min Act: -0.0004

Data Index: 645089 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0248. Min Act: -0.0003

Data Index: 1185857 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0242. Min Act: -0.0003

Data Index: 1245023 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0231. Min Act: -0.0004

Data Index: 1259848 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0235. Min Act: -0.0003

Data Index: 1356904 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0238. Min Act: -0.0003

Data Index: 930728 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0254. Min Act: -0.0003

Data Index: 381847 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0242. Min Act: -0.0003

Data Index: 667977 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0236. Min Act: -0.0003

Data Index: 1322564 (C4 (Web Text))

Max Activating Token Index: 472

Text #14

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0232. Min Act: -0.0003

Data Index: 303395 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0252. Min Act: -0.0003

Data Index: 686884 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0232. Min Act: -0.0003

Data Index: 109871 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0272. Min Act: -0.0003

Data Index: 467891 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0254. Min Act: -0.0003

Data Index: 1291157 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0256. Min Act: -0.0003

Data Index: 275006 (C4 (Web Text))

Max Activating Token Index: 162