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

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

Neuron 3427 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0286. Min Act: -0.0003

Data Index: 1255257 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0264. Min Act: -0.0003

Data Index: 285284 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0258. Min Act: -0.0003

Data Index: 1198873 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0245. Min Act: -0.0002

Data Index: 912216 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0261. Min Act: -0.0003

Data Index: 207063 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0258. Min Act: -0.0003

Data Index: 143970 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0246. Min Act: -0.0002

Data Index: 1192011 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0248. Min Act: -0.0002

Data Index: 1249930 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0245. Min Act: -0.0002

Data Index: 566879 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0237. Min Act: -0.0003

Data Index: 893185 (C4 (Web Text))

Max Activating Token Index: 136

Text #10

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0235. Min Act: -0.0002

Data Index: 1234016 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0244. Min Act: -0.0003

Data Index: 458042 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0218. Min Act: -0.0003

Data Index: 627960 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0229. Min Act: -0.0002

Data Index: 666752 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0233. Min Act: -0.0002

Data Index: 517227 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0237. Min Act: -0.0003

Data Index: 662804 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0237. Min Act: -0.0002

Data Index: 1019964 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0214. Min Act: -0.0003

Data Index: 1330605 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0223. Min Act: -0.0003

Data Index: 1214604 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0230. Min Act: -0.0003

Data Index: 493773 (C4 (Web Text))

Max Activating Token Index: 923