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

Dataset: The Pile

Neuron 3573 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: 0.5337. Min Range: -0.5337

Max Act: 0.5337. Min Act: -0.0000

Data Index: 55043 (The Pile)

Max Activating Token Index: 197

Text #1

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.4934. Min Act: -0.0000

Data Index: 1134009 (The Pile)

Max Activating Token Index: 1002

Text #2

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.3999. Min Act: -0.0000

Data Index: 551532 (The Pile)

Max Activating Token Index: 884

Text #3

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.3955. Min Act: -0.0000

Data Index: 1369598 (The Pile)

Max Activating Token Index: 516

Text #4

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.3883. Min Act: -0.0000

Data Index: 1116137 (The Pile)

Max Activating Token Index: 586

Text #5

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.3878. Min Act: -0.0000

Data Index: 776787 (The Pile)

Max Activating Token Index: 917

Text #6

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.3600. Min Act: -0.0000

Data Index: 266118 (The Pile)

Max Activating Token Index: 723

Text #7

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.3603. Min Act: -0.0000

Data Index: 1048052 (The Pile)

Max Activating Token Index: 444

Text #8

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.3251. Min Act: -0.0000

Data Index: 631159 (The Pile)

Max Activating Token Index: 723

Text #9

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.3411. Min Act: -0.0000

Data Index: 1285215 (The Pile)

Max Activating Token Index: 1006

Text #10

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.3278. Min Act: -0.0000

Data Index: 1516215 (The Pile)

Max Activating Token Index: 740

Text #11

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.3595. Min Act: -0.0000

Data Index: 425537 (The Pile)

Max Activating Token Index: 183

Text #12

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.3623. Min Act: -0.0000

Data Index: 156371 (The Pile)

Max Activating Token Index: 773

Text #13

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.3534. Min Act: -0.0000

Data Index: 1753697 (The Pile)

Max Activating Token Index: 556

Text #14

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.3229. Min Act: -0.0000

Data Index: 1906045 (The Pile)

Max Activating Token Index: 723

Text #15

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.3268. Min Act: -0.0000

Data Index: 774473 (The Pile)

Max Activating Token Index: 111

Text #16

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.3211. Min Act: -0.0000

Data Index: 1600062 (The Pile)

Max Activating Token Index: 566

Text #17

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.3380. Min Act: -0.0000

Data Index: 1460739 (The Pile)

Max Activating Token Index: 549

Text #18

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.2823. Min Act: -0.0000

Data Index: 1606356 (The Pile)

Max Activating Token Index: 998

Text #19

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.3057. Min Act: -0.0000

Data Index: 1756848 (The Pile)

Max Activating Token Index: 997