Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 585 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0451. Min Act: -0.0000

Data Index: 173872 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0391. Min Act: -0.0000

Data Index: 962772 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0404. Min Act: -0.0000

Data Index: 859011 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0368. Min Act: -0.0000

Data Index: 615206 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0309. Min Act: 0.0001

Data Index: 347486 (C4 (Web Text))

Max Activating Token Index: 1019

Text #5

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0321. Min Act: -0.0000

Data Index: 1440189 (Python Code)

Max Activating Token Index: 789

Text #6

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0315. Min Act: 0.0001

Data Index: 1509983 (Python Code)

Max Activating Token Index: 235

Text #7

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0322. Min Act: -0.0000

Data Index: 1216324 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0320. Min Act: -0.0000

Data Index: 796469 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0337. Min Act: -0.0000

Data Index: 1230092 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0301. Min Act: -0.0000

Data Index: 201981 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0282. Min Act: -0.0000

Data Index: 500675 (C4 (Web Text))

Max Activating Token Index: 862

Text #12

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0296. Min Act: -0.0000

Data Index: 31687 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0290. Min Act: -0.0000

Data Index: 457444 (C4 (Web Text))

Max Activating Token Index: 304

Text #14

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0309. Min Act: -0.0000

Data Index: 1284272 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0266. Min Act: -0.0000

Data Index: 740871 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0297. Min Act: -0.0000

Data Index: 704429 (C4 (Web Text))

Max Activating Token Index: 766

Text #17

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0301. Min Act: -0.0000

Data Index: 671277 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0276. Min Act: 0.0001

Data Index: 1611331 (Python Code)

Max Activating Token Index: 95

Text #19

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0274. Min Act: -0.0000

Data Index: 682061 (C4 (Web Text))

Max Activating Token Index: 243