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

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

Neuron 4291 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: 662063 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0191. Min Act: -0.0002

Data Index: 1334513 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0186. Min Act: -0.0002

Data Index: 1343615 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0184. Min Act: -0.0002

Data Index: 1194170 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0183. Min Act: -0.0002

Data Index: 369460 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0181. Min Act: -0.0002

Data Index: 894133 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0181. Min Act: -0.0002

Data Index: 445840 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0181. Min Act: -0.0002

Data Index: 524542 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0181. Min Act: -0.0002

Data Index: 636085 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0180. Min Act: -0.0002

Data Index: 397057 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0180. Min Act: -0.0002

Data Index: 255307 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0179. Min Act: -0.0002

Data Index: 40796 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0179. Min Act: -0.0002

Data Index: 687942 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0179. Min Act: -0.0002

Data Index: 84546 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0178. Min Act: -0.0002

Data Index: 858903 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0178. Min Act: -0.0002

Data Index: 398319 (C4 (Web Text))

Max Activating Token Index: 248

Text #16

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0178. Min Act: -0.0002

Data Index: 1243663 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0177. Min Act: -0.0002

Data Index: 716601 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0177. Min Act: -0.0002

Data Index: 1004656 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0176. Min Act: -0.0002

Data Index: 516976 (C4 (Web Text))

Max Activating Token Index: 541