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

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

Neuron 718 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0441. Min Act: -0.0003

Data Index: 940497 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0288. Min Act: -0.0003

Data Index: 858765 (C4 (Web Text))

Max Activating Token Index: 325

Text #2

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0277. Min Act: -0.0003

Data Index: 769204 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0264. Min Act: -0.0003

Data Index: 1166086 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0243. Min Act: -0.0002

Data Index: 1332016 (C4 (Web Text))

Max Activating Token Index: 795

Text #5

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0247. Min Act: -0.0003

Data Index: 34206 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0232. Min Act: -0.0003

Data Index: 390666 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0232. Min Act: -0.0003

Data Index: 393127 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0223. Min Act: -0.0003

Data Index: 961534 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0216. Min Act: -0.0002

Data Index: 1185236 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0219. Min Act: -0.0003

Data Index: 801807 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0222. Min Act: -0.0003

Data Index: 1218627 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0206. Min Act: -0.0003

Data Index: 1031773 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0203. Min Act: -0.0002

Data Index: 301377 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0205. Min Act: -0.0003

Data Index: 805520 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0204. Min Act: -0.0003

Data Index: 541579 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0206. Min Act: -0.0002

Data Index: 1262702 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0199. Min Act: -0.0003

Data Index: 1266919 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0204. Min Act: -0.0003

Data Index: 644112 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0196. Min Act: -0.0003

Data Index: 76065 (C4 (Web Text))

Max Activating Token Index: 780