Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3832 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.7908. Min Act: -0.0000

Data Index: 449870 (The Pile)

Max Activating Token Index: 353

Text #1

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.4536. Min Act: -0.0000

Data Index: 37761 (The Pile)

Max Activating Token Index: 729

Text #2

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.3721. Min Act: -0.0000

Data Index: 1247433 (The Pile)

Max Activating Token Index: 194

Text #3

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.3967. Min Act: -0.0000

Data Index: 431866 (The Pile)

Max Activating Token Index: 670

Text #4

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.0717. Min Act: -0.0000

Data Index: 1171810 (The Pile)

Max Activating Token Index: 65

Text #5

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.1193. Min Act: -0.0000

Data Index: 1913670 (The Pile)

Max Activating Token Index: 898

Text #6

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.1510. Min Act: -0.0000

Data Index: 577150 (The Pile)

Max Activating Token Index: 508

Text #7

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.2488. Min Act: -0.0000

Data Index: 45900 (The Pile)

Max Activating Token Index: 732

Text #8

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.0962. Min Act: -0.0000

Data Index: 734353 (The Pile)

Max Activating Token Index: 522

Text #9

Max Range: 1.7908. Min Range: -1.7908

Max Act: 0.9957. Min Act: -0.0000

Data Index: 1656028 (The Pile)

Max Activating Token Index: 816

Text #10

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.1748. Min Act: -0.0000

Data Index: 1855197 (The Pile)

Max Activating Token Index: 390

Text #11

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.0922. Min Act: -0.0000

Data Index: 551945 (The Pile)

Max Activating Token Index: 228

Text #12

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.2830. Min Act: -0.0000

Data Index: 520500 (The Pile)

Max Activating Token Index: 723

Text #13

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.1041. Min Act: -0.0000

Data Index: 1562837 (The Pile)

Max Activating Token Index: 639

Text #14

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.1797. Min Act: -0.0000

Data Index: 909348 (The Pile)

Max Activating Token Index: 1012

Text #15

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.0745. Min Act: -0.0000

Data Index: 1917162 (The Pile)

Max Activating Token Index: 501

Text #16

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.0014. Min Act: -0.0000

Data Index: 20937 (The Pile)

Max Activating Token Index: 731

Text #17

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.1021. Min Act: -0.0000

Data Index: 1762725 (The Pile)

Max Activating Token Index: 855

Text #18

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.0919. Min Act: -0.0000

Data Index: 1244667 (The Pile)

Max Activating Token Index: 844

Text #19

Max Range: 1.7908. Min Range: -1.7908

Max Act: 1.0460. Min Act: -0.0000

Data Index: 1717429 (The Pile)

Max Activating Token Index: 629