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

Dataset: The Pile

Neuron 948 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.7871. Min Act: -0.0000

Data Index: 549835 (The Pile)

Max Activating Token Index: 212

Text #1

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.7167. Min Act: -0.0000

Data Index: 756686 (The Pile)

Max Activating Token Index: 451

Text #2

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.6519. Min Act: -0.0000

Data Index: 170933 (The Pile)

Max Activating Token Index: 813

Text #3

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.7730. Min Act: -0.0000

Data Index: 1740237 (The Pile)

Max Activating Token Index: 596

Text #4

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.6537. Min Act: -0.0000

Data Index: 1967128 (The Pile)

Max Activating Token Index: 229

Text #5

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.6682. Min Act: -0.0000

Data Index: 1902891 (The Pile)

Max Activating Token Index: 380

Text #6

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.6397. Min Act: -0.0000

Data Index: 281689 (The Pile)

Max Activating Token Index: 177

Text #7

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.6047. Min Act: -0.0000

Data Index: 1073186 (The Pile)

Max Activating Token Index: 667

Text #8

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.5540. Min Act: -0.0000

Data Index: 1153681 (The Pile)

Max Activating Token Index: 105

Text #9

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.6039. Min Act: -0.0000

Data Index: 645182 (The Pile)

Max Activating Token Index: 660

Text #10

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.6128. Min Act: -0.0000

Data Index: 414819 (The Pile)

Max Activating Token Index: 770

Text #11

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.5783. Min Act: -0.0000

Data Index: 1191464 (The Pile)

Max Activating Token Index: 394

Text #12

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.4802. Min Act: -0.0000

Data Index: 668497 (The Pile)

Max Activating Token Index: 838

Text #13

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.4852. Min Act: -0.0000

Data Index: 928023 (The Pile)

Max Activating Token Index: 435

Text #14

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.5115. Min Act: -0.0000

Data Index: 1626728 (The Pile)

Max Activating Token Index: 611

Text #15

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.5171. Min Act: -0.0000

Data Index: 919120 (The Pile)

Max Activating Token Index: 432

Text #16

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.5258. Min Act: -0.0000

Data Index: 227667 (The Pile)

Max Activating Token Index: 546

Text #17

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.4458. Min Act: -0.0000

Data Index: 132615 (The Pile)

Max Activating Token Index: 759

Text #18

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.4597. Min Act: -0.0000

Data Index: 1377337 (The Pile)

Max Activating Token Index: 930

Text #19

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.4594. Min Act: -0.0000

Data Index: 405667 (The Pile)

Max Activating Token Index: 406