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

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

Neuron 322 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0417. Min Act: -0.0002

Data Index: 795897 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0393. Min Act: -0.0002

Data Index: 875231 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0350. Min Act: -0.0002

Data Index: 995589 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0349. Min Act: -0.0002

Data Index: 203773 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0341. Min Act: -0.0002

Data Index: 359657 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0315. Min Act: -0.0002

Data Index: 849115 (C4 (Web Text))

Max Activating Token Index: 931

Text #6

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0315. Min Act: -0.0002

Data Index: 61736 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0306. Min Act: -0.0002

Data Index: 1046812 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0298. Min Act: -0.0002

Data Index: 44593 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0297. Min Act: -0.0002

Data Index: 1280903 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0300. Min Act: -0.0002

Data Index: 817545 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0265. Min Act: -0.0002

Data Index: 313973 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0282. Min Act: -0.0002

Data Index: 510411 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0285. Min Act: -0.0002

Data Index: 787794 (C4 (Web Text))

Max Activating Token Index: 346

Text #14

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0282. Min Act: -0.0002

Data Index: 1003787 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0291. Min Act: -0.0002

Data Index: 920660 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0294. Min Act: -0.0002

Data Index: 1202233 (C4 (Web Text))

Max Activating Token Index: 674

Text #17

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0279. Min Act: -0.0002

Data Index: 1216530 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0285. Min Act: -0.0002

Data Index: 874601 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0276. Min Act: -0.0002

Data Index: 1233543 (C4 (Web Text))

Max Activating Token Index: 552