Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1753 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0255. Min Act: -0.0006

Data Index: 198549 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0209. Min Act: -0.0006

Data Index: 1314384 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0213. Min Act: -0.0006

Data Index: 307368 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0196. Min Act: -0.0006

Data Index: 165571 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0200. Min Act: -0.0006

Data Index: 66599 (C4 (Web Text))

Max Activating Token Index: 991

Text #5

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0186. Min Act: -0.0006

Data Index: 908574 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0190. Min Act: -0.0006

Data Index: 1224770 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0189. Min Act: -0.0006

Data Index: 154367 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0176. Min Act: -0.0006

Data Index: 956238 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0185. Min Act: -0.0006

Data Index: 454035 (C4 (Web Text))

Max Activating Token Index: 227

Text #10

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0172. Min Act: -0.0006

Data Index: 712302 (C4 (Web Text))

Max Activating Token Index: 611

Text #11

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0175. Min Act: -0.0006

Data Index: 793315 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0172. Min Act: -0.0006

Data Index: 979090 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0175. Min Act: -0.0006

Data Index: 1075784 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0165. Min Act: -0.0006

Data Index: 712117 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0169. Min Act: -0.0006

Data Index: 965522 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0172. Min Act: -0.0006

Data Index: 701681 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0164. Min Act: -0.0006

Data Index: 1303953 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0166. Min Act: -0.0006

Data Index: 1120502 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0165. Min Act: -0.0006

Data Index: 1180271 (C4 (Web Text))

Max Activating Token Index: 25