Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1640 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0467. Min Act: -0.0001

Data Index: 520251 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0449. Min Act: -0.0002

Data Index: 794278 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1206357 (C4 (Web Text))

Max Activating Token Index: 529

Text #3

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0413. Min Act: -0.0001

Data Index: 720061 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0415. Min Act: -0.0002

Data Index: 316362 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0396. Min Act: -0.0002

Data Index: 1076146 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0398. Min Act: -0.0002

Data Index: 143833 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0398. Min Act: -0.0001

Data Index: 436216 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0398. Min Act: -0.0001

Data Index: 136321 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0383. Min Act: -0.0002

Data Index: 101970 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0377. Min Act: -0.0002

Data Index: 270876 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0385. Min Act: -0.0002

Data Index: 707872 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0375. Min Act: -0.0002

Data Index: 1246552 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0378. Min Act: -0.0002

Data Index: 759044 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0380. Min Act: -0.0002

Data Index: 1162512 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0377. Min Act: -0.0002

Data Index: 857322 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0376. Min Act: -0.0001

Data Index: 584287 (C4 (Web Text))

Max Activating Token Index: 696

Text #17

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0375. Min Act: -0.0002

Data Index: 1293185 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0370. Min Act: -0.0001

Data Index: 89301 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0377. Min Act: -0.0002

Data Index: 941239 (C4 (Web Text))

Max Activating Token Index: 720