Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 653 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0237. Min Act: -0.0003

Data Index: 1029902 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0240. Min Act: -0.0003

Data Index: 835285 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0229. Min Act: -0.0003

Data Index: 207385 (C4 (Web Text))

Max Activating Token Index: 653

Text #3

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0184. Min Act: -0.0003

Data Index: 72381 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0180. Min Act: -0.0004

Data Index: 485615 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0183. Min Act: -0.0003

Data Index: 6077 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0182. Min Act: -0.0003

Data Index: 699123 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0193. Min Act: -0.0003

Data Index: 696721 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0185. Min Act: -0.0003

Data Index: 1302119 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0184. Min Act: -0.0003

Data Index: 214202 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0169. Min Act: -0.0003

Data Index: 33694 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0153. Min Act: -0.0003

Data Index: 200442 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0174. Min Act: -0.0003

Data Index: 754297 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0182. Min Act: -0.0003

Data Index: 290195 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0181. Min Act: -0.0003

Data Index: 240151 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0169. Min Act: -0.0003

Data Index: 1127100 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0169. Min Act: -0.0003

Data Index: 789330 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0164. Min Act: -0.0003

Data Index: 429365 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0173. Min Act: -0.0003

Data Index: 37884 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0177. Min Act: -0.0003

Data Index: 953237 (C4 (Web Text))

Max Activating Token Index: 340