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

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

Neuron 4350 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: 0.0196. Min Range: -0.0196

Max Act: 0.0196. Min Act: -0.0002

Data Index: 1251511 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0187. Min Act: -0.0002

Data Index: 911190 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0185. Min Act: -0.0002

Data Index: 874630 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0182. Min Act: -0.0002

Data Index: 430069 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0179. Min Act: -0.0002

Data Index: 575062 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0178. Min Act: -0.0002

Data Index: 285972 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0178. Min Act: -0.0002

Data Index: 668114 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0176. Min Act: -0.0002

Data Index: 863984 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0172. Min Act: -0.0002

Data Index: 572863 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0175. Min Act: -0.0002

Data Index: 1134990 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0172. Min Act: -0.0002

Data Index: 415569 (C4 (Web Text))

Max Activating Token Index: 338

Text #11

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0168. Min Act: -0.0002

Data Index: 1206330 (C4 (Web Text))

Max Activating Token Index: 266

Text #12

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0171. Min Act: -0.0002

Data Index: 620044 (C4 (Web Text))

Max Activating Token Index: 643

Text #13

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0166. Min Act: -0.0002

Data Index: 870883 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0170. Min Act: -0.0002

Data Index: 298323 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0172. Min Act: -0.0002

Data Index: 995895 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0169. Min Act: -0.0002

Data Index: 1269885 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0172. Min Act: -0.0002

Data Index: 1193655 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0168. Min Act: -0.0002

Data Index: 877246 (C4 (Web Text))

Max Activating Token Index: 68

Text #19

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0168. Min Act: -0.0002

Data Index: 1027891 (C4 (Web Text))

Max Activating Token Index: 173