Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3911 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.3186. Min Act: -0.0000

Data Index: 1163457 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2966. Min Act: -0.0000

Data Index: 90828 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2996. Min Act: -0.0000

Data Index: 57659 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2491. Min Act: -0.0000

Data Index: 1229974 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2620. Min Act: -0.0000

Data Index: 550264 (C4 (Web Text))

Max Activating Token Index: 297

Text #5

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2601. Min Act: -0.0000

Data Index: 1342081 (C4 (Web Text))

Max Activating Token Index: 603

Text #6

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2554. Min Act: -0.0000

Data Index: 310963 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2541. Min Act: -0.0000

Data Index: 575921 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2440. Min Act: -0.0000

Data Index: 644992 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2655. Min Act: -0.0000

Data Index: 422295 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2450. Min Act: -0.0000

Data Index: 131921 (C4 (Web Text))

Max Activating Token Index: 644

Text #11

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2355. Min Act: -0.0000

Data Index: 874350 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2488. Min Act: -0.0000

Data Index: 412880 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2413. Min Act: -0.0000

Data Index: 269824 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2416. Min Act: -0.0000

Data Index: 999036 (C4 (Web Text))

Max Activating Token Index: 211

Text #15

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2378. Min Act: -0.0000

Data Index: 1227195 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2439. Min Act: -0.0000

Data Index: 438561 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2370. Min Act: -0.0000

Data Index: 774295 (C4 (Web Text))

Max Activating Token Index: 321

Text #18

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2238. Min Act: -0.0000

Data Index: 1156339 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2395. Min Act: -0.0000

Data Index: 1162950 (C4 (Web Text))

Max Activating Token Index: 158