Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3232 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0302. Min Act: -0.0002

Data Index: 1232126 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0339. Min Act: -0.0002

Data Index: 1587299 (Python Code)

Max Activating Token Index: 352

Text #2

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0257. Min Act: -0.0002

Data Index: 367311 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0286. Min Act: -0.0002

Data Index: 996337 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0262. Min Act: -0.0002

Data Index: 1514571 (Python Code)

Max Activating Token Index: 655

Text #5

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0285. Min Act: -0.0002

Data Index: 1189992 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0291. Min Act: -0.0002

Data Index: 971338 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0277. Min Act: -0.0002

Data Index: 1208860 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0268. Min Act: -0.0002

Data Index: 203168 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0228. Min Act: -0.0002

Data Index: 425301 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0262. Min Act: -0.0002

Data Index: 707343 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0283. Min Act: -0.0002

Data Index: 1198751 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0254. Min Act: -0.0002

Data Index: 1275539 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0264. Min Act: -0.0002

Data Index: 1477561 (Python Code)

Max Activating Token Index: 269

Text #14

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0278. Min Act: -0.0002

Data Index: 1641479 (Python Code)

Max Activating Token Index: 122

Text #15

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0243. Min Act: -0.0002

Data Index: 291553 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0250. Min Act: -0.0002

Data Index: 282770 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0241. Min Act: -0.0002

Data Index: 1377639 (Python Code)

Max Activating Token Index: 831

Text #18

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0239. Min Act: -0.0002

Data Index: 940830 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0227. Min Act: -0.0002

Data Index: 1215941 (C4 (Web Text))

Max Activating Token Index: 743