Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3846 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0293. Min Act: -0.0002

Data Index: 630494 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0313. Min Act: -0.0002

Data Index: 414845 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0277. Min Act: -0.0002

Data Index: 1347898 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0264. Min Act: -0.0002

Data Index: 617476 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0264. Min Act: -0.0002

Data Index: 477089 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0246. Min Act: -0.0002

Data Index: 1098547 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0245. Min Act: -0.0002

Data Index: 857726 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0231. Min Act: -0.0002

Data Index: 821956 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0237. Min Act: -0.0002

Data Index: 715482 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0245. Min Act: -0.0002

Data Index: 394802 (C4 (Web Text))

Max Activating Token Index: 104

Text #10

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0235. Min Act: -0.0002

Data Index: 505272 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0231. Min Act: -0.0002

Data Index: 297961 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0245. Min Act: -0.0002

Data Index: 803439 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0219. Min Act: -0.0002

Data Index: 1102999 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0229. Min Act: -0.0002

Data Index: 39367 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0206. Min Act: -0.0002

Data Index: 539625 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0214. Min Act: -0.0002

Data Index: 301330 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0209. Min Act: -0.0002

Data Index: 958400 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0209. Min Act: -0.0002

Data Index: 429739 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0216. Min Act: -0.0002

Data Index: 521927 (C4 (Web Text))

Max Activating Token Index: 610