Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 162 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0264. Min Act: -0.0005

Data Index: 295966 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0259. Min Act: -0.0006

Data Index: 211461 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0259. Min Act: -0.0006

Data Index: 1085101 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0254. Min Act: -0.0007

Data Index: 781760 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0246. Min Act: -0.0006

Data Index: 1256797 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0245. Min Act: -0.0006

Data Index: 662380 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0241. Min Act: -0.0006

Data Index: 654949 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0238. Min Act: -0.0006

Data Index: 1302137 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0237. Min Act: -0.0006

Data Index: 316452 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0229. Min Act: -0.0006

Data Index: 392914 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0235. Min Act: -0.0006

Data Index: 308239 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0233. Min Act: -0.0006

Data Index: 1291011 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0232. Min Act: -0.0006

Data Index: 761088 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0227. Min Act: -0.0005

Data Index: 27526 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0231. Min Act: -0.0006

Data Index: 1053807 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0229. Min Act: -0.0006

Data Index: 315167 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0223. Min Act: -0.0006

Data Index: 718936 (C4 (Web Text))

Max Activating Token Index: 335

Text #17

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0228. Min Act: -0.0006

Data Index: 856088 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0228. Min Act: -0.0006

Data Index: 1313156 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0227. Min Act: -0.0006

Data Index: 147921 (C4 (Web Text))

Max Activating Token Index: 930