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

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

Neuron 48 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: 0.0214. Min Range: -0.0214

Max Act: 0.0214. Min Act: -0.0006

Data Index: 645045 (C4 (Web Text))

Max Activating Token Index: 532

Text #1

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0213. Min Act: -0.0006

Data Index: 665141 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0200. Min Act: -0.0006

Data Index: 491359 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0204. Min Act: -0.0006

Data Index: 978213 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0191. Min Act: -0.0006

Data Index: 306966 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0197. Min Act: -0.0006

Data Index: 1190713 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0198. Min Act: -0.0006

Data Index: 964198 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0185. Min Act: -0.0006

Data Index: 743238 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0196. Min Act: -0.0006

Data Index: 837408 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0190. Min Act: -0.0006

Data Index: 965703 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0197. Min Act: -0.0006

Data Index: 571379 (C4 (Web Text))

Max Activating Token Index: 536

Text #11

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0193. Min Act: -0.0006

Data Index: 7302 (C4 (Web Text))

Max Activating Token Index: 973

Text #12

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0192. Min Act: -0.0006

Data Index: 1195739 (C4 (Web Text))

Max Activating Token Index: 482

Text #13

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0195. Min Act: -0.0006

Data Index: 972796 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0192. Min Act: -0.0006

Data Index: 86010 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0184. Min Act: -0.0006

Data Index: 324891 (C4 (Web Text))

Max Activating Token Index: 149

Text #16

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0193. Min Act: -0.0006

Data Index: 717423 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0184. Min Act: -0.0006

Data Index: 738089 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0191. Min Act: -0.0006

Data Index: 1008956 (C4 (Web Text))

Max Activating Token Index: 679

Text #19

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0188. Min Act: -0.0006

Data Index: 591499 (C4 (Web Text))

Max Activating Token Index: 623