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

Dataset: The Pile

Neuron 751 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1667. Min Act: -0.0000

Data Index: 1944363 (The Pile)

Max Activating Token Index: 662

Text #1

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1837. Min Act: -0.0000

Data Index: 1974738 (The Pile)

Max Activating Token Index: 971

Text #2

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1813. Min Act: -0.0000

Data Index: 809323 (The Pile)

Max Activating Token Index: 906

Text #3

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1802. Min Act: -0.0000

Data Index: 1990838 (The Pile)

Max Activating Token Index: 935

Text #4

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1782. Min Act: -0.0000

Data Index: 495712 (The Pile)

Max Activating Token Index: 934

Text #5

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1766. Min Act: -0.0000

Data Index: 1851213 (The Pile)

Max Activating Token Index: 982

Text #6

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1724. Min Act: -0.0000

Data Index: 922088 (The Pile)

Max Activating Token Index: 859

Text #7

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1806. Min Act: -0.0000

Data Index: 748627 (The Pile)

Max Activating Token Index: 759

Text #8

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1577. Min Act: -0.0000

Data Index: 1576350 (The Pile)

Max Activating Token Index: 863

Text #9

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1692. Min Act: -0.0000

Data Index: 253459 (The Pile)

Max Activating Token Index: 989

Text #10

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1669. Min Act: -0.0000

Data Index: 810324 (The Pile)

Max Activating Token Index: 879

Text #11

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1875. Min Act: -0.0000

Data Index: 145900 (The Pile)

Max Activating Token Index: 799

Text #12

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1505. Min Act: -0.0000

Data Index: 105390 (The Pile)

Max Activating Token Index: 876

Text #13

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1510. Min Act: -0.0000

Data Index: 1879629 (The Pile)

Max Activating Token Index: 886

Text #14

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1378. Min Act: -0.0000

Data Index: 802215 (The Pile)

Max Activating Token Index: 817

Text #15

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1600. Min Act: -0.0000

Data Index: 886 (The Pile)

Max Activating Token Index: 677

Text #16

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1532. Min Act: -0.0000

Data Index: 1478927 (The Pile)

Max Activating Token Index: 948

Text #17

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1642. Min Act: -0.0000

Data Index: 1527478 (The Pile)

Max Activating Token Index: 505

Text #18

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1557. Min Act: -0.0000

Data Index: 308232 (The Pile)

Max Activating Token Index: 344

Text #19

Max Range: 0.1875. Min Range: -0.1875

Max Act: 0.1739. Min Act: -0.0000

Data Index: 886141 (The Pile)

Max Activating Token Index: 480