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

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

Neuron 3389 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: 0.0269. Min Range: -0.0269

Max Act: 0.0269. Min Act: -0.0002

Data Index: 355952 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0267. Min Act: -0.0003

Data Index: 531662 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0257. Min Act: -0.0003

Data Index: 470361 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0237. Min Act: -0.0003

Data Index: 826968 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0245. Min Act: -0.0003

Data Index: 678879 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0239. Min Act: -0.0003

Data Index: 123549 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0234. Min Act: -0.0003

Data Index: 794193 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0223. Min Act: -0.0003

Data Index: 251527 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0220. Min Act: -0.0003

Data Index: 875622 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0218. Min Act: -0.0003

Data Index: 679543 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0201. Min Act: -0.0003

Data Index: 1293274 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0205. Min Act: -0.0003

Data Index: 504990 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0196. Min Act: -0.0002

Data Index: 570189 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0198. Min Act: -0.0003

Data Index: 623126 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0197. Min Act: -0.0002

Data Index: 1094405 (C4 (Web Text))

Max Activating Token Index: 335

Text #15

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0191. Min Act: -0.0002

Data Index: 315452 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0184. Min Act: -0.0003

Data Index: 338446 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0184. Min Act: -0.0003

Data Index: 1173200 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0179. Min Act: -0.0003

Data Index: 703515 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0178. Min Act: -0.0003

Data Index: 1099740 (C4 (Web Text))

Max Activating Token Index: 380