Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 956 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0273. Min Act: -0.0004

Data Index: 975312 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0263. Min Act: -0.0004

Data Index: 1322614 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0247. Min Act: -0.0004

Data Index: 997792 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0236. Min Act: -0.0004

Data Index: 782791 (C4 (Web Text))

Max Activating Token Index: 676

Text #4

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0230. Min Act: -0.0004

Data Index: 942439 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0228. Min Act: -0.0004

Data Index: 735580 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0254. Min Act: -0.0004

Data Index: 678907 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0224. Min Act: -0.0004

Data Index: 548881 (C4 (Web Text))

Max Activating Token Index: 794

Text #8

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0258. Min Act: -0.0004

Data Index: 993023 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0265. Min Act: -0.0004

Data Index: 414849 (C4 (Web Text))

Max Activating Token Index: 704

Text #10

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0208. Min Act: -0.0004

Data Index: 1347835 (C4 (Web Text))

Max Activating Token Index: 259

Text #11

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0244. Min Act: -0.0004

Data Index: 604447 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0236. Min Act: -0.0004

Data Index: 1572884 (Python Code)

Max Activating Token Index: 429

Text #13

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0217. Min Act: -0.0004

Data Index: 784058 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0245. Min Act: -0.0004

Data Index: 572585 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0230. Min Act: -0.0004

Data Index: 599680 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0205. Min Act: -0.0004

Data Index: 451209 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0243. Min Act: -0.0004

Data Index: 87900 (C4 (Web Text))

Max Activating Token Index: 747

Text #18

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0227. Min Act: -0.0004

Data Index: 1627362 (Python Code)

Max Activating Token Index: 998

Text #19

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0226. Min Act: -0.0004

Data Index: 1501695 (Python Code)

Max Activating Token Index: 257