Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1793 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0208. Min Act: -0.0006

Data Index: 964591 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0205. Min Act: -0.0006

Data Index: 696284 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0191. Min Act: -0.0006

Data Index: 524384 (C4 (Web Text))

Max Activating Token Index: 934

Text #3

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0191. Min Act: -0.0006

Data Index: 68726 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0194. Min Act: -0.0006

Data Index: 510391 (C4 (Web Text))

Max Activating Token Index: 973

Text #5

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0182. Min Act: -0.0006

Data Index: 503034 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0181. Min Act: -0.0006

Data Index: 328269 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0181. Min Act: -0.0006

Data Index: 1079246 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0179. Min Act: -0.0006

Data Index: 705839 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0177. Min Act: -0.0006

Data Index: 296906 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0179. Min Act: -0.0006

Data Index: 285013 (C4 (Web Text))

Max Activating Token Index: 357

Text #11

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0175. Min Act: -0.0006

Data Index: 997720 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0174. Min Act: -0.0006

Data Index: 1341562 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0178. Min Act: -0.0006

Data Index: 1080584 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0173. Min Act: -0.0006

Data Index: 641259 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0180. Min Act: -0.0006

Data Index: 684285 (C4 (Web Text))

Max Activating Token Index: 482

Text #16

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0183. Min Act: -0.0005

Data Index: 363838 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0177. Min Act: -0.0006

Data Index: 85601 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0173. Min Act: -0.0006

Data Index: 479365 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0173. Min Act: -0.0006

Data Index: 844205 (C4 (Web Text))

Max Activating Token Index: 51