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

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

Neuron 2014 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0344. Min Act: -0.0002

Data Index: 321623 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0333. Min Act: -0.0002

Data Index: 1028361 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0280. Min Act: -0.0002

Data Index: 76197 (C4 (Web Text))

Max Activating Token Index: 449

Text #3

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0253. Min Act: -0.0002

Data Index: 798272 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0255. Min Act: -0.0002

Data Index: 25810 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0243. Min Act: -0.0002

Data Index: 1185178 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0241. Min Act: -0.0002

Data Index: 659913 (C4 (Web Text))

Max Activating Token Index: 430

Text #7

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0249. Min Act: -0.0002

Data Index: 330911 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0235. Min Act: -0.0002

Data Index: 111407 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0241. Min Act: -0.0002

Data Index: 1157178 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0240. Min Act: -0.0002

Data Index: 801374 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0231. Min Act: -0.0002

Data Index: 842864 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0231. Min Act: -0.0002

Data Index: 586282 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0230. Min Act: -0.0002

Data Index: 850540 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0232. Min Act: -0.0002

Data Index: 1357566 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0227. Min Act: -0.0002

Data Index: 224174 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0229. Min Act: -0.0002

Data Index: 196468 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0222. Min Act: -0.0002

Data Index: 467398 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0215. Min Act: -0.0002

Data Index: 1304867 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0216. Min Act: -0.0002

Data Index: 33828 (C4 (Web Text))

Max Activating Token Index: 360