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

Dataset: The Pile

Neuron 2163 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: 0.2588. Min Range: -0.2588

Max Act: 0.2553. Min Act: -0.0000

Data Index: 1064598 (The Pile)

Max Activating Token Index: 763

Text #1

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.2588. Min Act: -0.0000

Data Index: 1723015 (The Pile)

Max Activating Token Index: 696

Text #2

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1937. Min Act: -0.0000

Data Index: 1023156 (The Pile)

Max Activating Token Index: 994

Text #3

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1630. Min Act: -0.0000

Data Index: 812551 (The Pile)

Max Activating Token Index: 693

Text #4

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1982. Min Act: -0.0000

Data Index: 1638440 (The Pile)

Max Activating Token Index: 900

Text #5

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1863. Min Act: -0.0000

Data Index: 879453 (The Pile)

Max Activating Token Index: 397

Text #6

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1979. Min Act: -0.0000

Data Index: 1548694 (The Pile)

Max Activating Token Index: 1009

Text #7

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1744. Min Act: -0.0000

Data Index: 688401 (The Pile)

Max Activating Token Index: 970

Text #8

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1712. Min Act: -0.0000

Data Index: 1782165 (The Pile)

Max Activating Token Index: 898

Text #9

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1797. Min Act: -0.0000

Data Index: 1229947 (The Pile)

Max Activating Token Index: 862

Text #10

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1806. Min Act: -0.0000

Data Index: 1528209 (The Pile)

Max Activating Token Index: 606

Text #11

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1775. Min Act: -0.0000

Data Index: 1925616 (The Pile)

Max Activating Token Index: 551

Text #12

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1913. Min Act: -0.0000

Data Index: 182373 (The Pile)

Max Activating Token Index: 945

Text #13

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1814. Min Act: -0.0000

Data Index: 685320 (The Pile)

Max Activating Token Index: 959

Text #14

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1816. Min Act: -0.0000

Data Index: 877364 (The Pile)

Max Activating Token Index: 939

Text #15

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1747. Min Act: -0.0000

Data Index: 230592 (The Pile)

Max Activating Token Index: 696

Text #16

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1630. Min Act: -0.0000

Data Index: 1945664 (The Pile)

Max Activating Token Index: 787

Text #17

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1688. Min Act: -0.0000

Data Index: 1553989 (The Pile)

Max Activating Token Index: 625

Text #18

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1847. Min Act: -0.0000

Data Index: 1337941 (The Pile)

Max Activating Token Index: 964

Text #19

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1723. Min Act: -0.0000

Data Index: 113678 (The Pile)

Max Activating Token Index: 174