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

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

Neuron 2032 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3760. Min Act: -0.0000

Data Index: 594285 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3380. Min Act: -0.0000

Data Index: 408171 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3393. Min Act: -0.0000

Data Index: 1320869 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3205. Min Act: -0.0000

Data Index: 616662 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2999. Min Act: -0.0000

Data Index: 80924 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3041. Min Act: -0.0000

Data Index: 858407 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2903. Min Act: -0.0000

Data Index: 728725 (C4 (Web Text))

Max Activating Token Index: 484

Text #7

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2849. Min Act: -0.0000

Data Index: 309267 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2696. Min Act: -0.0000

Data Index: 551204 (C4 (Web Text))

Max Activating Token Index: 564

Text #9

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2760. Min Act: -0.0000

Data Index: 410703 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2616. Min Act: -0.0000

Data Index: 214067 (C4 (Web Text))

Max Activating Token Index: 771

Text #11

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2783. Min Act: 0.0000

Data Index: 818229 (C4 (Web Text))

Max Activating Token Index: 73

Text #12

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2404. Min Act: -0.0000

Data Index: 3382 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2614. Min Act: -0.0000

Data Index: 1035572 (C4 (Web Text))

Max Activating Token Index: 999

Text #14

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2436. Min Act: -0.0000

Data Index: 446428 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2563. Min Act: -0.0000

Data Index: 576286 (C4 (Web Text))

Max Activating Token Index: 413

Text #16

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2662. Min Act: -0.0000

Data Index: 377801 (C4 (Web Text))

Max Activating Token Index: 635

Text #17

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2503. Min Act: -0.0000

Data Index: 340262 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2254. Min Act: -0.0000

Data Index: 200871 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2453. Min Act: -0.0000

Data Index: 529970 (C4 (Web Text))

Max Activating Token Index: 164