Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4115 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0416. Min Act: -0.0000

Data Index: 54077 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0287. Min Act: -0.0000

Data Index: 229839 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0269. Min Act: -0.0000

Data Index: 279781 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0286. Min Act: -0.0000

Data Index: 640263 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0264. Min Act: -0.0000

Data Index: 574736 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0272. Min Act: -0.0000

Data Index: 111487 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0280. Min Act: -0.0000

Data Index: 40360 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0233. Min Act: -0.0000

Data Index: 825653 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0267. Min Act: -0.0000

Data Index: 30562 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0262. Min Act: -0.0000

Data Index: 1204229 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0245. Min Act: -0.0000

Data Index: 227369 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0271. Min Act: -0.0000

Data Index: 788615 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0247. Min Act: -0.0000

Data Index: 189918 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0254. Min Act: -0.0000

Data Index: 1511699 (Python Code)

Max Activating Token Index: 547

Text #14

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0237. Min Act: -0.0000

Data Index: 50164 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0241. Min Act: -0.0000

Data Index: 218982 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0238. Min Act: -0.0000

Data Index: 330846 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0229. Min Act: -0.0000

Data Index: 943480 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0228. Min Act: -0.0000

Data Index: 1017941 (C4 (Web Text))

Max Activating Token Index: 354

Text #19

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0235. Min Act: -0.0000

Data Index: 280880 (C4 (Web Text))

Max Activating Token Index: 351