Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1828 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0228. Min Act: -0.0004

Data Index: 1300155 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0213. Min Act: -0.0004

Data Index: 513092 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0211. Min Act: -0.0004

Data Index: 1249979 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0209. Min Act: -0.0004

Data Index: 1018736 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0209. Min Act: -0.0004

Data Index: 444202 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0207. Min Act: -0.0004

Data Index: 761421 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0202. Min Act: -0.0004

Data Index: 409447 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0204. Min Act: -0.0004

Data Index: 113315 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0203. Min Act: -0.0005

Data Index: 477054 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0201. Min Act: -0.0004

Data Index: 1071461 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0200. Min Act: -0.0004

Data Index: 533545 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0199. Min Act: -0.0004

Data Index: 174170 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0198. Min Act: -0.0004

Data Index: 1341994 (C4 (Web Text))

Max Activating Token Index: 561

Text #13

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0196. Min Act: -0.0005

Data Index: 1030704 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0195. Min Act: -0.0004

Data Index: 1024333 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0191. Min Act: -0.0004

Data Index: 112171 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0194. Min Act: -0.0004

Data Index: 324102 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0195. Min Act: -0.0005

Data Index: 1289295 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0190. Min Act: -0.0005

Data Index: 600250 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0189. Min Act: -0.0004

Data Index: 232387 (C4 (Web Text))

Max Activating Token Index: 19