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

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

Neuron 44 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: 0.0281. Min Range: -0.0281

Max Act: 0.0271. Min Act: -0.0006

Data Index: 519585 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0277. Min Act: -0.0006

Data Index: 1208916 (C4 (Web Text))

Max Activating Token Index: 529

Text #2

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0281. Min Act: -0.0006

Data Index: 832052 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0259. Min Act: -0.0006

Data Index: 907225 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0265. Min Act: -0.0006

Data Index: 175212 (C4 (Web Text))

Max Activating Token Index: 293

Text #5

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0264. Min Act: -0.0006

Data Index: 26318 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0256. Min Act: -0.0006

Data Index: 554518 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0255. Min Act: -0.0006

Data Index: 271058 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0258. Min Act: -0.0006

Data Index: 849477 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0258. Min Act: -0.0006

Data Index: 645495 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0257. Min Act: -0.0006

Data Index: 1161264 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0257. Min Act: -0.0006

Data Index: 190178 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0245. Min Act: -0.0006

Data Index: 906208 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0250. Min Act: -0.0006

Data Index: 1286033 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0252. Min Act: -0.0006

Data Index: 231209 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0251. Min Act: -0.0006

Data Index: 90641 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0251. Min Act: -0.0006

Data Index: 1044124 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0250. Min Act: -0.0006

Data Index: 1094660 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0255. Min Act: -0.0006

Data Index: 1071755 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0241. Min Act: -0.0006

Data Index: 731971 (C4 (Web Text))

Max Activating Token Index: 629