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

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

Neuron 2350 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: 0.0231. Min Range: -0.0231

Max Act: 0.0231. Min Act: -0.0003

Data Index: 967475 (C4 (Web Text))

Max Activating Token Index: 340

Text #1

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0194. Min Act: -0.0003

Data Index: 225051 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0206. Min Act: -0.0002

Data Index: 859193 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0183. Min Act: -0.0003

Data Index: 567000 (C4 (Web Text))

Max Activating Token Index: 592

Text #4

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0181. Min Act: -0.0003

Data Index: 1358740 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0179. Min Act: -0.0003

Data Index: 1354276 (C4 (Web Text))

Max Activating Token Index: 854

Text #6

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0176. Min Act: -0.0002

Data Index: 1197501 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0180. Min Act: -0.0003

Data Index: 393571 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0180. Min Act: -0.0002

Data Index: 75301 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0184. Min Act: -0.0003

Data Index: 563026 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0181. Min Act: -0.0003

Data Index: 1057153 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0167. Min Act: -0.0003

Data Index: 574192 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0174. Min Act: -0.0003

Data Index: 246659 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0173. Min Act: -0.0003

Data Index: 172984 (C4 (Web Text))

Max Activating Token Index: 736

Text #14

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0170. Min Act: -0.0003

Data Index: 674312 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0166. Min Act: -0.0002

Data Index: 1167115 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0177. Min Act: -0.0003

Data Index: 443291 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0171. Min Act: -0.0003

Data Index: 515587 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0164. Min Act: -0.0002

Data Index: 1240889 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0170. Min Act: -0.0002

Data Index: 1208924 (C4 (Web Text))

Max Activating Token Index: 771