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

Dataset: The Pile

Neuron 3868 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.2982. Min Act: 0.0000

Data Index: 397047 (The Pile)

Max Activating Token Index: 1022

Text #1

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.2702. Min Act: 0.0000

Data Index: 1889031 (The Pile)

Max Activating Token Index: 781

Text #2

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.2915. Min Act: 0.0000

Data Index: 1417763 (The Pile)

Max Activating Token Index: 816

Text #3

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.2665. Min Act: 0.0000

Data Index: 129514 (The Pile)

Max Activating Token Index: 796

Text #4

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.2478. Min Act: 0.0000

Data Index: 1505324 (The Pile)

Max Activating Token Index: 1021

Text #5

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.2251. Min Act: 0.0000

Data Index: 3137 (The Pile)

Max Activating Token Index: 694

Text #6

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.2219. Min Act: -0.0000

Data Index: 1161042 (The Pile)

Max Activating Token Index: 663

Text #7

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.1875. Min Act: -0.0000

Data Index: 550702 (The Pile)

Max Activating Token Index: 643

Text #8

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.1893. Min Act: -0.0000

Data Index: 1840157 (The Pile)

Max Activating Token Index: 631

Text #9

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.2060. Min Act: -0.0000

Data Index: 1202886 (The Pile)

Max Activating Token Index: 377

Text #10

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.2026. Min Act: -0.0000

Data Index: 71777 (The Pile)

Max Activating Token Index: 906

Text #11

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.1761. Min Act: -0.0000

Data Index: 1855322 (The Pile)

Max Activating Token Index: 658

Text #12

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.2084. Min Act: -0.0000

Data Index: 194865 (The Pile)

Max Activating Token Index: 925

Text #13

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.1922. Min Act: -0.0000

Data Index: 1327177 (The Pile)

Max Activating Token Index: 91

Text #14

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.2053. Min Act: -0.0000

Data Index: 422089 (The Pile)

Max Activating Token Index: 709

Text #15

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.1587. Min Act: -0.0000

Data Index: 1253127 (The Pile)

Max Activating Token Index: 963

Text #16

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.1934. Min Act: -0.0000

Data Index: 964020 (The Pile)

Max Activating Token Index: 775

Text #17

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.1668. Min Act: -0.0000

Data Index: 1925687 (The Pile)

Max Activating Token Index: 391

Text #18

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.1774. Min Act: -0.0000

Data Index: 1144056 (The Pile)

Max Activating Token Index: 891

Text #19

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.1977. Min Act: -0.0000

Data Index: 1882891 (The Pile)

Max Activating Token Index: 697