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

Dataset: The Pile

Neuron 2699 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1353. Min Range: -3.1353

Max Act: 3.1353. Min Act: -0.0000

Data Index: 1434596 (The Pile)

Max Activating Token Index: 273

Text #1

Max Range: 3.1353. Min Range: -3.1353

Max Act: 2.9112. Min Act: -0.0000

Data Index: 1416090 (The Pile)

Max Activating Token Index: 436

Text #2

Max Range: 3.1353. Min Range: -3.1353

Max Act: 2.7513. Min Act: -0.0000

Data Index: 1134138 (The Pile)

Max Activating Token Index: 230

Text #3

Max Range: 3.1353. Min Range: -3.1353

Max Act: 2.8597. Min Act: -0.0000

Data Index: 878035 (The Pile)

Max Activating Token Index: 476

Text #4

Max Range: 3.1353. Min Range: -3.1353

Max Act: 2.8207. Min Act: -0.0000

Data Index: 1642066 (The Pile)

Max Activating Token Index: 66

Text #5

Max Range: 3.1353. Min Range: -3.1353

Max Act: 2.8363. Min Act: -0.0000

Data Index: 1080006 (The Pile)

Max Activating Token Index: 911

Text #6

Max Range: 3.1353. Min Range: -3.1353

Max Act: 2.4299. Min Act: -0.0000

Data Index: 1666555 (The Pile)

Max Activating Token Index: 700

Text #7

Max Range: 3.1353. Min Range: -3.1353

Max Act: 2.5082. Min Act: -0.0000

Data Index: 329202 (The Pile)

Max Activating Token Index: 923

Text #8

Max Range: 3.1353. Min Range: -3.1353

Max Act: 2.5274. Min Act: -0.0000

Data Index: 849409 (The Pile)

Max Activating Token Index: 81

Text #9

Max Range: 3.1353. Min Range: -3.1353

Max Act: 2.4205. Min Act: -0.0000

Data Index: 358436 (The Pile)

Max Activating Token Index: 382

Text #10

Max Range: 3.1353. Min Range: -3.1353

Max Act: 2.3858. Min Act: -0.0000

Data Index: 1059758 (The Pile)

Max Activating Token Index: 866

Text #11

Max Range: 3.1353. Min Range: -3.1353

Max Act: 2.3519. Min Act: -0.0000

Data Index: 1913588 (The Pile)

Max Activating Token Index: 367

Text #12

Max Range: 3.1353. Min Range: -3.1353

Max Act: 2.3632. Min Act: -0.0000

Data Index: 1907379 (The Pile)

Max Activating Token Index: 421

Text #13

Max Range: 3.1353. Min Range: -3.1353

Max Act: 2.3606. Min Act: -0.0000

Data Index: 1289312 (The Pile)

Max Activating Token Index: 124

Text #14

Max Range: 3.1353. Min Range: -3.1353

Max Act: 2.3553. Min Act: -0.0000

Data Index: 796277 (The Pile)

Max Activating Token Index: 347

Text #15

Max Range: 3.1353. Min Range: -3.1353

Max Act: 2.3162. Min Act: -0.0000

Data Index: 976132 (The Pile)

Max Activating Token Index: 425

Text #16

Max Range: 3.1353. Min Range: -3.1353

Max Act: 2.4323. Min Act: -0.0000

Data Index: 1091999 (The Pile)

Max Activating Token Index: 83

Text #17

Max Range: 3.1353. Min Range: -3.1353

Max Act: 2.3106. Min Act: -0.0000

Data Index: 943438 (The Pile)

Max Activating Token Index: 999

Text #18

Max Range: 3.1353. Min Range: -3.1353

Max Act: 2.1649. Min Act: -0.0000

Data Index: 331185 (The Pile)

Max Activating Token Index: 53

Text #19

Max Range: 3.1353. Min Range: -3.1353

Max Act: 2.3782. Min Act: -0.0000

Data Index: 1199769 (The Pile)

Max Activating Token Index: 53