Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 144 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0362. Min Act: -0.0003

Data Index: 5583 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0222. Min Act: -0.0003

Data Index: 85640 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0207. Min Act: -0.0003

Data Index: 577375 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0226. Min Act: -0.0003

Data Index: 221868 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0199. Min Act: -0.0003

Data Index: 341601 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0198. Min Act: -0.0003

Data Index: 1248600 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0158. Min Act: -0.0003

Data Index: 757906 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0180. Min Act: -0.0003

Data Index: 986262 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0208. Min Act: -0.0003

Data Index: 1172107 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0173. Min Act: -0.0003

Data Index: 695408 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0169. Min Act: -0.0003

Data Index: 57525 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0173. Min Act: -0.0003

Data Index: 848995 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0169. Min Act: -0.0003

Data Index: 1605457 (Python Code)

Max Activating Token Index: 918

Text #13

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0167. Min Act: -0.0003

Data Index: 1032493 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0174. Min Act: -0.0003

Data Index: 1289515 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0157. Min Act: -0.0003

Data Index: 1068692 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0157. Min Act: -0.0003

Data Index: 1321640 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0145. Min Act: -0.0003

Data Index: 663629 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0161. Min Act: -0.0003

Data Index: 395385 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0185. Min Act: -0.0003

Data Index: 104247 (C4 (Web Text))

Max Activating Token Index: 941