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

Dataset: The Pile

Neuron 476 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2352. Min Range: -1.2352

Max Act: 1.2352. Min Act: -0.0000

Data Index: 83531 (The Pile)

Max Activating Token Index: 556

Text #1

Max Range: 1.2352. Min Range: -1.2352

Max Act: 1.1467. Min Act: -0.0000

Data Index: 139439 (The Pile)

Max Activating Token Index: 599

Text #2

Max Range: 1.2352. Min Range: -1.2352

Max Act: 1.0653. Min Act: -0.0000

Data Index: 1907585 (The Pile)

Max Activating Token Index: 702

Text #3

Max Range: 1.2352. Min Range: -1.2352

Max Act: 1.0378. Min Act: -0.0000

Data Index: 1303649 (The Pile)

Max Activating Token Index: 165

Text #4

Max Range: 1.2352. Min Range: -1.2352

Max Act: 0.9542. Min Act: -0.0000

Data Index: 1316084 (The Pile)

Max Activating Token Index: 205

Text #5

Max Range: 1.2352. Min Range: -1.2352

Max Act: 1.0048. Min Act: -0.0000

Data Index: 1924194 (The Pile)

Max Activating Token Index: 643

Text #6

Max Range: 1.2352. Min Range: -1.2352

Max Act: 0.9953. Min Act: -0.0000

Data Index: 1949810 (The Pile)

Max Activating Token Index: 96

Text #7

Max Range: 1.2352. Min Range: -1.2352

Max Act: 0.9916. Min Act: -0.0000

Data Index: 830780 (The Pile)

Max Activating Token Index: 62

Text #8

Max Range: 1.2352. Min Range: -1.2352

Max Act: 0.9701. Min Act: -0.0000

Data Index: 1306842 (The Pile)

Max Activating Token Index: 954

Text #9

Max Range: 1.2352. Min Range: -1.2352

Max Act: 0.9732. Min Act: -0.0000

Data Index: 1576536 (The Pile)

Max Activating Token Index: 291

Text #10

Max Range: 1.2352. Min Range: -1.2352

Max Act: 0.9716. Min Act: -0.0000

Data Index: 1786093 (The Pile)

Max Activating Token Index: 661

Text #11

Max Range: 1.2352. Min Range: -1.2352

Max Act: 0.8771. Min Act: -0.0000

Data Index: 373849 (The Pile)

Max Activating Token Index: 61

Text #12

Max Range: 1.2352. Min Range: -1.2352

Max Act: 0.9055. Min Act: -0.0000

Data Index: 988734 (The Pile)

Max Activating Token Index: 25

Text #13

Max Range: 1.2352. Min Range: -1.2352

Max Act: 0.8400. Min Act: -0.0000

Data Index: 1396832 (The Pile)

Max Activating Token Index: 795

Text #14

Max Range: 1.2352. Min Range: -1.2352

Max Act: 0.9493. Min Act: -0.0000

Data Index: 252588 (The Pile)

Max Activating Token Index: 987

Text #15

Max Range: 1.2352. Min Range: -1.2352

Max Act: 0.8336. Min Act: -0.0000

Data Index: 657697 (The Pile)

Max Activating Token Index: 867

Text #16

Max Range: 1.2352. Min Range: -1.2352

Max Act: 0.8926. Min Act: -0.0000

Data Index: 1214488 (The Pile)

Max Activating Token Index: 231

Text #17

Max Range: 1.2352. Min Range: -1.2352

Max Act: 0.8839. Min Act: -0.0000

Data Index: 506098 (The Pile)

Max Activating Token Index: 194

Text #18

Max Range: 1.2352. Min Range: -1.2352

Max Act: 0.8337. Min Act: -0.0000

Data Index: 164080 (The Pile)

Max Activating Token Index: 964

Text #19

Max Range: 1.2352. Min Range: -1.2352

Max Act: 0.8812. Min Act: 0.0000

Data Index: 1919044 (The Pile)

Max Activating Token Index: 23