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

Dataset: The Pile

Neuron 1241 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.4893. Min Act: -0.0000

Data Index: 150569 (The Pile)

Max Activating Token Index: 636

Text #1

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.4301. Min Act: -0.0000

Data Index: 750855 (The Pile)

Max Activating Token Index: 510

Text #2

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3812. Min Act: -0.0000

Data Index: 254286 (The Pile)

Max Activating Token Index: 691

Text #3

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.4128. Min Act: -0.0000

Data Index: 1923209 (The Pile)

Max Activating Token Index: 299

Text #4

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3970. Min Act: -0.0000

Data Index: 172899 (The Pile)

Max Activating Token Index: 182

Text #5

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3748. Min Act: -0.0000

Data Index: 1604998 (The Pile)

Max Activating Token Index: 389

Text #6

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3484. Min Act: -0.0000

Data Index: 1030705 (The Pile)

Max Activating Token Index: 673

Text #7

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3677. Min Act: -0.0000

Data Index: 1237386 (The Pile)

Max Activating Token Index: 375

Text #8

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3555. Min Act: -0.0000

Data Index: 561057 (The Pile)

Max Activating Token Index: 558

Text #9

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3628. Min Act: -0.0000

Data Index: 663023 (The Pile)

Max Activating Token Index: 326

Text #10

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3582. Min Act: -0.0000

Data Index: 103071 (The Pile)

Max Activating Token Index: 528

Text #11

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3565. Min Act: -0.0000

Data Index: 1771596 (The Pile)

Max Activating Token Index: 841

Text #12

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3406. Min Act: -0.0000

Data Index: 1276726 (The Pile)

Max Activating Token Index: 367

Text #13

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3282. Min Act: -0.0000

Data Index: 1731494 (The Pile)

Max Activating Token Index: 759

Text #14

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3370. Min Act: -0.0000

Data Index: 1154566 (The Pile)

Max Activating Token Index: 401

Text #15

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3288. Min Act: -0.0000

Data Index: 778222 (The Pile)

Max Activating Token Index: 99

Text #16

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3461. Min Act: -0.0000

Data Index: 1116191 (The Pile)

Max Activating Token Index: 527

Text #17

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3229. Min Act: -0.0000

Data Index: 1977159 (The Pile)

Max Activating Token Index: 365

Text #18

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3640. Min Act: -0.0000

Data Index: 2861 (The Pile)

Max Activating Token Index: 813

Text #19

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3752. Min Act: -0.0000

Data Index: 1797680 (The Pile)

Max Activating Token Index: 514