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

Dataset: The Pile

Neuron 3534 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: 0.7925. Min Range: -0.7925

Max Act: 0.7925. Min Act: -0.0000

Data Index: 933539 (The Pile)

Max Activating Token Index: 437

Text #1

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.7620. Min Act: -0.0000

Data Index: 736837 (The Pile)

Max Activating Token Index: 652

Text #2

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.7231. Min Act: -0.0000

Data Index: 1382329 (The Pile)

Max Activating Token Index: 63

Text #3

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.7639. Min Act: -0.0000

Data Index: 267621 (The Pile)

Max Activating Token Index: 111

Text #4

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.7752. Min Act: -0.0000

Data Index: 1341136 (The Pile)

Max Activating Token Index: 794

Text #5

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.7511. Min Act: -0.0000

Data Index: 110209 (The Pile)

Max Activating Token Index: 249

Text #6

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.6823. Min Act: -0.0000

Data Index: 830982 (The Pile)

Max Activating Token Index: 958

Text #7

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.6971. Min Act: 0.0000

Data Index: 507355 (The Pile)

Max Activating Token Index: 104

Text #8

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.7124. Min Act: -0.0000

Data Index: 791387 (The Pile)

Max Activating Token Index: 247

Text #9

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.6894. Min Act: -0.0000

Data Index: 823686 (The Pile)

Max Activating Token Index: 556

Text #10

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.6872. Min Act: -0.0000

Data Index: 117533 (The Pile)

Max Activating Token Index: 937

Text #11

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.6338. Min Act: -0.0000

Data Index: 1224921 (The Pile)

Max Activating Token Index: 279

Text #12

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.6646. Min Act: -0.0000

Data Index: 1276111 (The Pile)

Max Activating Token Index: 809

Text #13

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.6427. Min Act: -0.0000

Data Index: 12347 (The Pile)

Max Activating Token Index: 612

Text #14

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.6689. Min Act: -0.0000

Data Index: 415526 (The Pile)

Max Activating Token Index: 383

Text #15

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.5870. Min Act: -0.0000

Data Index: 1686914 (The Pile)

Max Activating Token Index: 175

Text #16

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.6578. Min Act: -0.0000

Data Index: 1695554 (The Pile)

Max Activating Token Index: 982

Text #17

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.6100. Min Act: -0.0000

Data Index: 1836096 (The Pile)

Max Activating Token Index: 79

Text #18

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.5427. Min Act: -0.0000

Data Index: 985987 (The Pile)

Max Activating Token Index: 110

Text #19

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.5708. Min Act: -0.0000

Data Index: 712360 (The Pile)

Max Activating Token Index: 268