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

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

Neuron 772 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0451. Min Act: -0.0003

Data Index: 132404 (C4 (Web Text))

Max Activating Token Index: 631

Text #1

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0403. Min Act: -0.0003

Data Index: 981081 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0390. Min Act: -0.0002

Data Index: 213337 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0390. Min Act: -0.0003

Data Index: 442081 (C4 (Web Text))

Max Activating Token Index: 202

Text #4

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0395. Min Act: -0.0003

Data Index: 50728 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0383. Min Act: -0.0003

Data Index: 17144 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0376. Min Act: -0.0003

Data Index: 153847 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0380. Min Act: -0.0003

Data Index: 679393 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0380. Min Act: -0.0003

Data Index: 84295 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0379. Min Act: -0.0003

Data Index: 1224456 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0378. Min Act: -0.0003

Data Index: 1172384 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0377. Min Act: -0.0003

Data Index: 225493 (C4 (Web Text))

Max Activating Token Index: 460

Text #12

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0359. Min Act: -0.0003

Data Index: 1173085 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0362. Min Act: -0.0003

Data Index: 623756 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0357. Min Act: -0.0001

Data Index: 123087 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0358. Min Act: -0.0003

Data Index: 594513 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0363. Min Act: -0.0003

Data Index: 190086 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0363. Min Act: -0.0002

Data Index: 1250745 (C4 (Web Text))

Max Activating Token Index: 221

Text #18

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0364. Min Act: -0.0003

Data Index: 327304 (C4 (Web Text))

Max Activating Token Index: 897

Text #19

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0363. Min Act: -0.0004

Data Index: 453980 (C4 (Web Text))

Max Activating Token Index: 213