Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2903 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0277. Min Act: -0.0003

Data Index: 46911 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0271. Min Act: -0.0003

Data Index: 571662 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0243. Min Act: -0.0003

Data Index: 1153672 (C4 (Web Text))

Max Activating Token Index: 581

Text #3

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0245. Min Act: -0.0003

Data Index: 168415 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0236. Min Act: -0.0003

Data Index: 80596 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0226. Min Act: -0.0003

Data Index: 880140 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0230. Min Act: -0.0004

Data Index: 844287 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0225. Min Act: -0.0003

Data Index: 648942 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0233. Min Act: -0.0004

Data Index: 758234 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0224. Min Act: -0.0003

Data Index: 1321521 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0228. Min Act: -0.0003

Data Index: 987650 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0222. Min Act: -0.0003

Data Index: 477058 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0226. Min Act: -0.0003

Data Index: 417367 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0217. Min Act: -0.0003

Data Index: 1281827 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0210. Min Act: -0.0003

Data Index: 459515 (C4 (Web Text))

Max Activating Token Index: 634

Text #15

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0214. Min Act: -0.0003

Data Index: 766525 (C4 (Web Text))

Max Activating Token Index: 473

Text #16

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0212. Min Act: -0.0003

Data Index: 541425 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0211. Min Act: -0.0003

Data Index: 489868 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0210. Min Act: -0.0002

Data Index: 871288 (C4 (Web Text))

Max Activating Token Index: 721

Text #19

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0205. Min Act: -0.0004

Data Index: 299244 (C4 (Web Text))

Max Activating Token Index: 342