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

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

Neuron 1862 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: 0.0313. Min Range: -0.0313

Max Act: 0.0293. Min Act: -0.0006

Data Index: 895705 (C4 (Web Text))

Max Activating Token Index: 698

Text #1

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0306. Min Act: -0.0006

Data Index: 195367 (C4 (Web Text))

Max Activating Token Index: 473

Text #2

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0313. Min Act: -0.0006

Data Index: 490863 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0298. Min Act: -0.0006

Data Index: 862496 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0297. Min Act: -0.0006

Data Index: 53297 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0285. Min Act: -0.0006

Data Index: 390813 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0276. Min Act: -0.0006

Data Index: 389737 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0286. Min Act: -0.0006

Data Index: 1153966 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0278. Min Act: -0.0006

Data Index: 897983 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0280. Min Act: -0.0006

Data Index: 884680 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0281. Min Act: -0.0006

Data Index: 1074164 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0291. Min Act: -0.0006

Data Index: 846067 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0267. Min Act: -0.0006

Data Index: 677267 (C4 (Web Text))

Max Activating Token Index: 645

Text #13

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0271. Min Act: -0.0006

Data Index: 1097702 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0275. Min Act: -0.0006

Data Index: 571128 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0270. Min Act: -0.0005

Data Index: 1124654 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0275. Min Act: -0.0006

Data Index: 896801 (C4 (Web Text))

Max Activating Token Index: 336

Text #17

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0269. Min Act: -0.0006

Data Index: 584420 (C4 (Web Text))

Max Activating Token Index: 464

Text #18

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0268. Min Act: -0.0006

Data Index: 545470 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0279. Min Act: -0.0006

Data Index: 668254 (C4 (Web Text))

Max Activating Token Index: 511