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

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

Neuron 3830 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0364. Min Act: -0.0003

Data Index: 426015 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0271. Min Act: -0.0002

Data Index: 1134191 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0257. Min Act: -0.0003

Data Index: 644668 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0250. Min Act: -0.0003

Data Index: 486627 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0238. Min Act: -0.0003

Data Index: 499799 (C4 (Web Text))

Max Activating Token Index: 355

Text #5

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0238. Min Act: -0.0002

Data Index: 270429 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0234. Min Act: -0.0003

Data Index: 1007691 (C4 (Web Text))

Max Activating Token Index: 950

Text #7

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0223. Min Act: -0.0003

Data Index: 634453 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0222. Min Act: -0.0003

Data Index: 1288630 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0229. Min Act: -0.0003

Data Index: 408386 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0216. Min Act: -0.0003

Data Index: 1086038 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0219. Min Act: -0.0002

Data Index: 493972 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0213. Min Act: -0.0003

Data Index: 575848 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0215. Min Act: -0.0002

Data Index: 253446 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0211. Min Act: -0.0003

Data Index: 519361 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0217. Min Act: -0.0003

Data Index: 1245894 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0209. Min Act: -0.0003

Data Index: 1267294 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0208. Min Act: -0.0003

Data Index: 718059 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0205. Min Act: -0.0002

Data Index: 236343 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0203. Min Act: -0.0003

Data Index: 128055 (C4 (Web Text))

Max Activating Token Index: 123