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

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

Neuron 3539 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0312. Min Act: -0.0000

Data Index: 1258888 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0264. Min Act: -0.0000

Data Index: 438325 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0282. Min Act: -0.0000

Data Index: 354984 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0281. Min Act: -0.0000

Data Index: 1586825 (Python Code)

Max Activating Token Index: 84

Text #4

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0256. Min Act: -0.0000

Data Index: 1512926 (Python Code)

Max Activating Token Index: 441

Text #5

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0273. Min Act: -0.0000

Data Index: 235308 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0271. Min Act: -0.0000

Data Index: 138651 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0294. Min Act: -0.0000

Data Index: 981773 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0275. Min Act: -0.0000

Data Index: 589357 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0255. Min Act: -0.0000

Data Index: 166152 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0252. Min Act: -0.0000

Data Index: 360281 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0264. Min Act: -0.0000

Data Index: 208889 (C4 (Web Text))

Max Activating Token Index: 110

Text #12

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0263. Min Act: -0.0000

Data Index: 882792 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0265. Min Act: -0.0000

Data Index: 1413800 (Python Code)

Max Activating Token Index: 957

Text #14

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0251. Min Act: -0.0000

Data Index: 405633 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0256. Min Act: -0.0000

Data Index: 702716 (C4 (Web Text))

Max Activating Token Index: 566

Text #16

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0266. Min Act: -0.0000

Data Index: 811593 (C4 (Web Text))

Max Activating Token Index: 358

Text #17

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0257. Min Act: -0.0000

Data Index: 1647499 (Python Code)

Max Activating Token Index: 605

Text #18

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0247. Min Act: -0.0000

Data Index: 252879 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0255. Min Act: -0.0000

Data Index: 251790 (C4 (Web Text))

Max Activating Token Index: 980