Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2360 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0252. Min Act: -0.0003

Data Index: 488193 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0205. Min Act: -0.0003

Data Index: 867365 (C4 (Web Text))

Max Activating Token Index: 592

Text #2

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0208. Min Act: -0.0003

Data Index: 1140956 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0182. Min Act: -0.0004

Data Index: 1102800 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0181. Min Act: -0.0003

Data Index: 53387 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0209. Min Act: -0.0003

Data Index: 716536 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0180. Min Act: -0.0003

Data Index: 421915 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0153. Min Act: -0.0003

Data Index: 918066 (C4 (Web Text))

Max Activating Token Index: 720

Text #8

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0180. Min Act: -0.0003

Data Index: 932769 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0196. Min Act: -0.0003

Data Index: 1264939 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0179. Min Act: -0.0003

Data Index: 1193104 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0134. Min Act: -0.0003

Data Index: 476749 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0169. Min Act: -0.0004

Data Index: 179851 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0181. Min Act: -0.0003

Data Index: 387849 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0133. Min Act: -0.0003

Data Index: 1247996 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0159. Min Act: -0.0004

Data Index: 454906 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0181. Min Act: -0.0003

Data Index: 118440 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0141. Min Act: -0.0004

Data Index: 381537 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0131. Min Act: -0.0003

Data Index: 138075 (C4 (Web Text))

Max Activating Token Index: 967

Text #19

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0181. Min Act: -0.0004

Data Index: 432997 (C4 (Web Text))

Max Activating Token Index: 335