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

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

Neuron 992 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0254. Min Act: -0.0002

Data Index: 29321 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0208. Min Act: -0.0002

Data Index: 145448 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0205. Min Act: -0.0002

Data Index: 457594 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0187. Min Act: -0.0002

Data Index: 627587 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0185. Min Act: -0.0002

Data Index: 742236 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0179. Min Act: -0.0002

Data Index: 912347 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0178. Min Act: -0.0002

Data Index: 1137326 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0176. Min Act: -0.0002

Data Index: 1071936 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0174. Min Act: -0.0002

Data Index: 357408 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0173. Min Act: -0.0002

Data Index: 424169 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0173. Min Act: -0.0002

Data Index: 519413 (C4 (Web Text))

Max Activating Token Index: 725

Text #11

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0173. Min Act: -0.0002

Data Index: 1305899 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0175. Min Act: -0.0002

Data Index: 623494 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0175. Min Act: -0.0002

Data Index: 774307 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0170. Min Act: -0.0002

Data Index: 762682 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0167. Min Act: -0.0002

Data Index: 113699 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0169. Min Act: -0.0002

Data Index: 1264126 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0168. Min Act: -0.0002

Data Index: 202661 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0168. Min Act: -0.0002

Data Index: 1091413 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0168. Min Act: -0.0002

Data Index: 195719 (C4 (Web Text))

Max Activating Token Index: 8