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

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

Neuron 1988 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0226. Min Act: -0.0006

Data Index: 1109183 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0215. Min Act: -0.0006

Data Index: 952733 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0211. Min Act: -0.0006

Data Index: 508531 (C4 (Web Text))

Max Activating Token Index: 855

Text #3

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0210. Min Act: -0.0005

Data Index: 306898 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0200. Min Act: -0.0006

Data Index: 375498 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0196. Min Act: -0.0006

Data Index: 850378 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0199. Min Act: -0.0006

Data Index: 704749 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0189. Min Act: -0.0006

Data Index: 148076 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0199. Min Act: -0.0006

Data Index: 1112816 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0195. Min Act: -0.0006

Data Index: 474388 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0189. Min Act: -0.0006

Data Index: 22826 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0189. Min Act: -0.0006

Data Index: 25682 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0186. Min Act: -0.0006

Data Index: 799919 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0188. Min Act: -0.0006

Data Index: 1356972 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0192. Min Act: -0.0006

Data Index: 665409 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0179. Min Act: -0.0006

Data Index: 588375 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0182. Min Act: -0.0006

Data Index: 791997 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0183. Min Act: -0.0006

Data Index: 1003906 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0178. Min Act: -0.0006

Data Index: 185615 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0174. Min Act: -0.0006

Data Index: 95105 (C4 (Web Text))

Max Activating Token Index: 15