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

Dataset: The Pile

Neuron 1190 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1882. Min Act: -0.0000

Data Index: 521769 (The Pile)

Max Activating Token Index: 360

Text #1

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.2090. Min Act: -0.0000

Data Index: 1396303 (The Pile)

Max Activating Token Index: 523

Text #2

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.2003. Min Act: -0.0000

Data Index: 1392329 (The Pile)

Max Activating Token Index: 913

Text #3

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1783. Min Act: -0.0000

Data Index: 292756 (The Pile)

Max Activating Token Index: 744

Text #4

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1786. Min Act: -0.0000

Data Index: 1599430 (The Pile)

Max Activating Token Index: 540

Text #5

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1658. Min Act: -0.0000

Data Index: 1095956 (The Pile)

Max Activating Token Index: 739

Text #6

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1707. Min Act: -0.0000

Data Index: 262945 (The Pile)

Max Activating Token Index: 634

Text #7

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1711. Min Act: -0.0000

Data Index: 1452234 (The Pile)

Max Activating Token Index: 596

Text #8

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1620. Min Act: -0.0000

Data Index: 1090964 (The Pile)

Max Activating Token Index: 114

Text #9

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1660. Min Act: -0.0000

Data Index: 1544272 (The Pile)

Max Activating Token Index: 227

Text #10

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1622. Min Act: -0.0000

Data Index: 1247552 (The Pile)

Max Activating Token Index: 890

Text #11

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1686. Min Act: -0.0000

Data Index: 344666 (The Pile)

Max Activating Token Index: 835

Text #12

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1636. Min Act: -0.0000

Data Index: 80475 (The Pile)

Max Activating Token Index: 667

Text #13

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1656. Min Act: -0.0000

Data Index: 512792 (The Pile)

Max Activating Token Index: 769

Text #14

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1661. Min Act: -0.0000

Data Index: 1978872 (The Pile)

Max Activating Token Index: 135

Text #15

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1547. Min Act: -0.0000

Data Index: 1372741 (The Pile)

Max Activating Token Index: 722

Text #16

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1603. Min Act: -0.0000

Data Index: 1784967 (The Pile)

Max Activating Token Index: 212

Text #17

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1602. Min Act: -0.0000

Data Index: 1343390 (The Pile)

Max Activating Token Index: 881

Text #18

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1559. Min Act: -0.0000

Data Index: 1230117 (The Pile)

Max Activating Token Index: 467

Text #19

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1464. Min Act: -0.0000

Data Index: 1851681 (The Pile)

Max Activating Token Index: 263