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

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

Neuron 1075 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0260. Min Act: -0.0003

Data Index: 924105 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0264. Min Act: -0.0003

Data Index: 348913 (C4 (Web Text))

Max Activating Token Index: 286

Text #2

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0258. Min Act: -0.0004

Data Index: 888545 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0259. Min Act: -0.0004

Data Index: 894903 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0251. Min Act: -0.0003

Data Index: 1073579 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0248. Min Act: -0.0003

Data Index: 1329811 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0246. Min Act: -0.0003

Data Index: 1192054 (C4 (Web Text))

Max Activating Token Index: 508

Text #7

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0246. Min Act: -0.0004

Data Index: 616390 (C4 (Web Text))

Max Activating Token Index: 794

Text #8

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0244. Min Act: -0.0004

Data Index: 728044 (C4 (Web Text))

Max Activating Token Index: 680

Text #9

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0241. Min Act: -0.0003

Data Index: 647672 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0244. Min Act: -0.0003

Data Index: 27922 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0241. Min Act: -0.0003

Data Index: 16003 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0242. Min Act: -0.0003

Data Index: 714318 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0233. Min Act: -0.0003

Data Index: 802347 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0237. Min Act: -0.0004

Data Index: 441676 (C4 (Web Text))

Max Activating Token Index: 493

Text #15

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0237. Min Act: -0.0003

Data Index: 1124790 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0235. Min Act: -0.0003

Data Index: 994797 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0238. Min Act: -0.0004

Data Index: 1216337 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0235. Min Act: -0.0004

Data Index: 119643 (C4 (Web Text))

Max Activating Token Index: 245

Text #19

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0235. Min Act: -0.0003

Data Index: 458869 (C4 (Web Text))

Max Activating Token Index: 374