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

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

Neuron 4108 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0329. Min Act: -0.0001

Data Index: 211411 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0280. Min Act: -0.0001

Data Index: 628893 (C4 (Web Text))

Max Activating Token Index: 559

Text #2

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0276. Min Act: -0.0002

Data Index: 1037020 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0209. Min Act: -0.0001

Data Index: 1113729 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0213. Min Act: -0.0002

Data Index: 782689 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0242. Min Act: -0.0001

Data Index: 1297548 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0202. Min Act: -0.0001

Data Index: 514506 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0221. Min Act: -0.0001

Data Index: 177061 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0219. Min Act: -0.0001

Data Index: 1332059 (C4 (Web Text))

Max Activating Token Index: 984

Text #9

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0193. Min Act: -0.0001

Data Index: 196692 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0204. Min Act: -0.0001

Data Index: 659487 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0196. Min Act: -0.0001

Data Index: 939843 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0200. Min Act: -0.0001

Data Index: 547007 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0144. Min Act: -0.0001

Data Index: 748346 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0215. Min Act: -0.0001

Data Index: 212079 (C4 (Web Text))

Max Activating Token Index: 800

Text #15

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0193. Min Act: -0.0001

Data Index: 521760 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0181. Min Act: -0.0001

Data Index: 1250758 (C4 (Web Text))

Max Activating Token Index: 477

Text #17

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0136. Min Act: -0.0001

Data Index: 770318 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0176. Min Act: -0.0001

Data Index: 649200 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0177. Min Act: -0.0001

Data Index: 775238 (C4 (Web Text))

Max Activating Token Index: 15