Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 111 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0230. Min Act: -0.0005

Data Index: 675030 (C4 (Web Text))

Max Activating Token Index: 672

Text #1

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0223. Min Act: -0.0005

Data Index: 262778 (C4 (Web Text))

Max Activating Token Index: 868

Text #2

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0210. Min Act: -0.0005

Data Index: 879105 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0214. Min Act: -0.0005

Data Index: 822474 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0222. Min Act: -0.0005

Data Index: 736001 (C4 (Web Text))

Max Activating Token Index: 588

Text #5

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0224. Min Act: -0.0005

Data Index: 127570 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0218. Min Act: -0.0005

Data Index: 782782 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0222. Min Act: -0.0005

Data Index: 804295 (C4 (Web Text))

Max Activating Token Index: 526

Text #8

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0206. Min Act: -0.0005

Data Index: 1125322 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0203. Min Act: -0.0005

Data Index: 617697 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0202. Min Act: -0.0005

Data Index: 4366 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0203. Min Act: -0.0005

Data Index: 820769 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0206. Min Act: -0.0005

Data Index: 510381 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0217. Min Act: -0.0005

Data Index: 1154995 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0202. Min Act: -0.0005

Data Index: 262077 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0207. Min Act: -0.0005

Data Index: 1332202 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0198. Min Act: -0.0005

Data Index: 872933 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0193. Min Act: -0.0005

Data Index: 159389 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0199. Min Act: -0.0005

Data Index: 1006100 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0201. Min Act: -0.0005

Data Index: 1090324 (C4 (Web Text))

Max Activating Token Index: 473