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

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

Neuron 291 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: 0.0524. Min Range: -0.0524

Max Act: 0.0524. Min Act: -0.0006

Data Index: 1071570 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0380. Min Act: -0.0006

Data Index: 707850 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0364. Min Act: -0.0006

Data Index: 1089960 (C4 (Web Text))

Max Activating Token Index: 540

Text #3

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0360. Min Act: -0.0006

Data Index: 659573 (C4 (Web Text))

Max Activating Token Index: 228

Text #4

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0372. Min Act: -0.0006

Data Index: 934943 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0355. Min Act: -0.0006

Data Index: 1061792 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0318. Min Act: -0.0006

Data Index: 460953 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0321. Min Act: -0.0006

Data Index: 1179234 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0330. Min Act: -0.0006

Data Index: 795379 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0323. Min Act: -0.0006

Data Index: 794297 (C4 (Web Text))

Max Activating Token Index: 1003

Text #10

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0334. Min Act: -0.0006

Data Index: 868119 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0309. Min Act: -0.0006

Data Index: 548543 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0303. Min Act: -0.0006

Data Index: 1490983 (Python Code)

Max Activating Token Index: 454

Text #13

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0321. Min Act: -0.0006

Data Index: 315466 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0302. Min Act: -0.0006

Data Index: 138587 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0313. Min Act: -0.0006

Data Index: 349371 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0305. Min Act: -0.0006

Data Index: 317367 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0325. Min Act: -0.0006

Data Index: 62023 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0310. Min Act: -0.0006

Data Index: 607937 (C4 (Web Text))

Max Activating Token Index: 992

Text #19

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0321. Min Act: -0.0006

Data Index: 1068092 (C4 (Web Text))

Max Activating Token Index: 986