Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 42 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0246. Min Act: -0.0006

Data Index: 591476 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0230. Min Act: -0.0006

Data Index: 659764 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0210. Min Act: -0.0006

Data Index: 109533 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0206. Min Act: -0.0006

Data Index: 212339 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0198. Min Act: -0.0006

Data Index: 567010 (C4 (Web Text))

Max Activating Token Index: 588

Text #5

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0202. Min Act: -0.0006

Data Index: 184354 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0197. Min Act: -0.0006

Data Index: 53406 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0195. Min Act: -0.0006

Data Index: 684534 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0207. Min Act: -0.0006

Data Index: 1000091 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0197. Min Act: -0.0006

Data Index: 600132 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0195. Min Act: -0.0006

Data Index: 790189 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0199. Min Act: -0.0006

Data Index: 789509 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0196. Min Act: -0.0005

Data Index: 68446 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0188. Min Act: -0.0006

Data Index: 219728 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0189. Min Act: -0.0006

Data Index: 668395 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0193. Min Act: -0.0006

Data Index: 1262507 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0188. Min Act: -0.0006

Data Index: 973642 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0182. Min Act: -0.0005

Data Index: 375083 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0181. Min Act: -0.0006

Data Index: 335652 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0190. Min Act: -0.0006

Data Index: 142892 (C4 (Web Text))

Max Activating Token Index: 820