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

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

Neuron 1165 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: 0.0234. Min Range: -0.0234

Max Act: 0.0234. Min Act: -0.0006

Data Index: 86400 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0210. Min Act: -0.0006

Data Index: 1120026 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0199. Min Act: -0.0006

Data Index: 1046555 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0199. Min Act: -0.0006

Data Index: 497690 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0201. Min Act: -0.0006

Data Index: 839012 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0199. Min Act: -0.0006

Data Index: 227247 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0198. Min Act: -0.0006

Data Index: 711575 (C4 (Web Text))

Max Activating Token Index: 699

Text #7

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0198. Min Act: -0.0007

Data Index: 337654 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0196. Min Act: -0.0006

Data Index: 180228 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0195. Min Act: -0.0006

Data Index: 608583 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0194. Min Act: -0.0006

Data Index: 887662 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0193. Min Act: -0.0006

Data Index: 1201307 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0194. Min Act: -0.0006

Data Index: 677979 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0193. Min Act: -0.0006

Data Index: 1050156 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0191. Min Act: -0.0006

Data Index: 594538 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0190. Min Act: -0.0006

Data Index: 1303338 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0189. Min Act: -0.0006

Data Index: 646728 (C4 (Web Text))

Max Activating Token Index: 809

Text #17

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0188. Min Act: -0.0006

Data Index: 774701 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0188. Min Act: -0.0006

Data Index: 1250315 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0187. Min Act: -0.0006

Data Index: 661201 (C4 (Web Text))

Max Activating Token Index: 441