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

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

Neuron 5028 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1055369 (C4 (Web Text))

Max Activating Token Index: 706

Text #1

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0231. Min Act: -0.0002

Data Index: 712765 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0196. Min Act: -0.0002

Data Index: 863438 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0186. Min Act: -0.0002

Data Index: 541362 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0195. Min Act: -0.0002

Data Index: 1073328 (C4 (Web Text))

Max Activating Token Index: 448

Text #5

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0198. Min Act: -0.0002

Data Index: 1210822 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0196. Min Act: -0.0002

Data Index: 583714 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0177. Min Act: -0.0002

Data Index: 593626 (C4 (Web Text))

Max Activating Token Index: 434

Text #8

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0178. Min Act: -0.0002

Data Index: 677362 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0181. Min Act: -0.0002

Data Index: 427646 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0184. Min Act: -0.0002

Data Index: 249355 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0186. Min Act: -0.0002

Data Index: 206775 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0179. Min Act: -0.0002

Data Index: 1603518 (Python Code)

Max Activating Token Index: 569

Text #13

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0211. Min Act: -0.0002

Data Index: 495488 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0179. Min Act: -0.0002

Data Index: 1386528 (Python Code)

Max Activating Token Index: 582

Text #15

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0124. Min Act: -0.0002

Data Index: 1192735 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0173. Min Act: -0.0002

Data Index: 1184059 (C4 (Web Text))

Max Activating Token Index: 574

Text #17

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0165. Min Act: -0.0002

Data Index: 624342 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0178. Min Act: -0.0002

Data Index: 701018 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0174. Min Act: -0.0002

Data Index: 96243 (C4 (Web Text))

Max Activating Token Index: 170