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

Dataset: The Pile

Neuron 699 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: 0.3755. Min Range: -0.3755

Max Act: 0.3711. Min Act: -0.0000

Data Index: 1350032 (The Pile)

Max Activating Token Index: 950

Text #1

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3755. Min Act: -0.0000

Data Index: 1141876 (The Pile)

Max Activating Token Index: 421

Text #2

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3468. Min Act: -0.0000

Data Index: 51027 (The Pile)

Max Activating Token Index: 335

Text #3

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3100. Min Act: -0.0000

Data Index: 387010 (The Pile)

Max Activating Token Index: 1012

Text #4

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2532. Min Act: -0.0000

Data Index: 829929 (The Pile)

Max Activating Token Index: 585

Text #5

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2250. Min Act: -0.0000

Data Index: 1517505 (The Pile)

Max Activating Token Index: 797

Text #6

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2330. Min Act: -0.0000

Data Index: 1872461 (The Pile)

Max Activating Token Index: 709

Text #7

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.1999. Min Act: -0.0000

Data Index: 1224025 (The Pile)

Max Activating Token Index: 24

Text #8

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2119. Min Act: -0.0000

Data Index: 626974 (The Pile)

Max Activating Token Index: 660

Text #9

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.1895. Min Act: -0.0000

Data Index: 1501342 (The Pile)

Max Activating Token Index: 750

Text #10

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2014. Min Act: -0.0000

Data Index: 1865757 (The Pile)

Max Activating Token Index: 785

Text #11

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.1742. Min Act: -0.0000

Data Index: 1895321 (The Pile)

Max Activating Token Index: 688

Text #12

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2056. Min Act: -0.0000

Data Index: 1965632 (The Pile)

Max Activating Token Index: 867

Text #13

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.1944. Min Act: -0.0000

Data Index: 1458564 (The Pile)

Max Activating Token Index: 984

Text #14

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2027. Min Act: -0.0000

Data Index: 1504507 (The Pile)

Max Activating Token Index: 503

Text #15

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.1903. Min Act: -0.0000

Data Index: 1395616 (The Pile)

Max Activating Token Index: 734

Text #16

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.1856. Min Act: -0.0000

Data Index: 701984 (The Pile)

Max Activating Token Index: 362

Text #17

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.1875. Min Act: -0.0000

Data Index: 1010707 (The Pile)

Max Activating Token Index: 916

Text #18

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.1923. Min Act: -0.0000

Data Index: 1953728 (The Pile)

Max Activating Token Index: 923

Text #19

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.1699. Min Act: -0.0000

Data Index: 868424 (The Pile)

Max Activating Token Index: 973