Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1797 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.1903. Min Act: 0.0000

Data Index: 1494484 (The Pile)

Max Activating Token Index: 726

Text #1

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.1971. Min Act: -0.0000

Data Index: 1608313 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.1031. Min Act: -0.0000

Data Index: 1700220 (The Pile)

Max Activating Token Index: 867

Text #3

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.0752. Min Act: -0.0000

Data Index: 1857611 (The Pile)

Max Activating Token Index: 754

Text #4

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.0487. Min Act: -0.0000

Data Index: 511607 (The Pile)

Max Activating Token Index: 493

Text #5

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9518. Min Act: -0.0000

Data Index: 655908 (The Pile)

Max Activating Token Index: 626

Text #6

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9771. Min Act: -0.0000

Data Index: 614570 (The Pile)

Max Activating Token Index: 896

Text #7

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9820. Min Act: -0.0000

Data Index: 1691909 (The Pile)

Max Activating Token Index: 511

Text #8

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9689. Min Act: -0.0000

Data Index: 1289670 (The Pile)

Max Activating Token Index: 793

Text #9

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9645. Min Act: -0.0000

Data Index: 282872 (The Pile)

Max Activating Token Index: 112

Text #10

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9413. Min Act: -0.0000

Data Index: 1808518 (The Pile)

Max Activating Token Index: 647

Text #11

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9578. Min Act: 0.0000

Data Index: 1279866 (The Pile)

Max Activating Token Index: 803

Text #12

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9602. Min Act: -0.0000

Data Index: 955342 (The Pile)

Max Activating Token Index: 1011

Text #13

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.1090. Min Act: -0.0000

Data Index: 1786871 (The Pile)

Max Activating Token Index: 648

Text #14

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9319. Min Act: -0.0000

Data Index: 987111 (The Pile)

Max Activating Token Index: 83

Text #15

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.8885. Min Act: -0.0000

Data Index: 1627935 (The Pile)

Max Activating Token Index: 667

Text #16

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9327. Min Act: -0.0000

Data Index: 215787 (The Pile)

Max Activating Token Index: 33

Text #17

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9054. Min Act: -0.0000

Data Index: 1118564 (The Pile)

Max Activating Token Index: 814

Text #18

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.8961. Min Act: -0.0000

Data Index: 1614517 (The Pile)

Max Activating Token Index: 471

Text #19

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9367. Min Act: 0.0000

Data Index: 341573 (The Pile)

Max Activating Token Index: 484