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

Dataset: The Pile

Neuron 4566 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0335. Min Range: -1.0335

Max Act: 1.0335. Min Act: -0.0000

Data Index: 1886588 (The Pile)

Max Activating Token Index: 670

Text #1

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.9781. Min Act: -0.0000

Data Index: 1552343 (The Pile)

Max Activating Token Index: 544

Text #2

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.9589. Min Act: -0.0000

Data Index: 517703 (The Pile)

Max Activating Token Index: 93

Text #3

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.9134. Min Act: -0.0000

Data Index: 1792504 (The Pile)

Max Activating Token Index: 576

Text #4

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.8988. Min Act: -0.0000

Data Index: 87806 (The Pile)

Max Activating Token Index: 25

Text #5

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.8741. Min Act: -0.0000

Data Index: 246924 (The Pile)

Max Activating Token Index: 223

Text #6

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.7815. Min Act: -0.0000

Data Index: 1841645 (The Pile)

Max Activating Token Index: 640

Text #7

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.8166. Min Act: -0.0000

Data Index: 586242 (The Pile)

Max Activating Token Index: 314

Text #8

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.7701. Min Act: -0.0000

Data Index: 1517247 (The Pile)

Max Activating Token Index: 966

Text #9

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.8200. Min Act: -0.0000

Data Index: 539520 (The Pile)

Max Activating Token Index: 277

Text #10

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.8027. Min Act: -0.0000

Data Index: 1943894 (The Pile)

Max Activating Token Index: 432

Text #11

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.7759. Min Act: -0.0000

Data Index: 853950 (The Pile)

Max Activating Token Index: 603

Text #12

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.7358. Min Act: -0.0000

Data Index: 131325 (The Pile)

Max Activating Token Index: 413

Text #13

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.7667. Min Act: -0.0000

Data Index: 1951953 (The Pile)

Max Activating Token Index: 527

Text #14

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.7646. Min Act: -0.0000

Data Index: 1467609 (The Pile)

Max Activating Token Index: 732

Text #15

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.7162. Min Act: -0.0000

Data Index: 1629866 (The Pile)

Max Activating Token Index: 674

Text #16

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.7571. Min Act: -0.0000

Data Index: 1869266 (The Pile)

Max Activating Token Index: 975

Text #17

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.7602. Min Act: -0.0000

Data Index: 98177 (The Pile)

Max Activating Token Index: 611

Text #18

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.7553. Min Act: -0.0000

Data Index: 338556 (The Pile)

Max Activating Token Index: 493

Text #19

Max Range: 1.0335. Min Range: -1.0335

Max Act: 0.7512. Min Act: -0.0000

Data Index: 1091153 (The Pile)

Max Activating Token Index: 273