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

Dataset: The Pile

Neuron 3161 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1930. Min Act: -0.0000

Data Index: 703536 (The Pile)

Max Activating Token Index: 343

Text #1

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1819. Min Act: -0.0000

Data Index: 1062008 (The Pile)

Max Activating Token Index: 527

Text #2

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1764. Min Act: -0.0000

Data Index: 445591 (The Pile)

Max Activating Token Index: 587

Text #3

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1810. Min Act: -0.0000

Data Index: 1456859 (The Pile)

Max Activating Token Index: 931

Text #4

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1855. Min Act: -0.0000

Data Index: 661552 (The Pile)

Max Activating Token Index: 863

Text #5

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1812. Min Act: -0.0000

Data Index: 376877 (The Pile)

Max Activating Token Index: 726

Text #6

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1847. Min Act: -0.0000

Data Index: 1356986 (The Pile)

Max Activating Token Index: 511

Text #7

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1758. Min Act: -0.0000

Data Index: 1995083 (The Pile)

Max Activating Token Index: 902

Text #8

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1667. Min Act: -0.0000

Data Index: 1719748 (The Pile)

Max Activating Token Index: 869

Text #9

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1834. Min Act: -0.0000

Data Index: 1812177 (The Pile)

Max Activating Token Index: 312

Text #10

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1636. Min Act: -0.0000

Data Index: 59796 (The Pile)

Max Activating Token Index: 256

Text #11

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1712. Min Act: -0.0000

Data Index: 979385 (The Pile)

Max Activating Token Index: 310

Text #12

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1681. Min Act: -0.0000

Data Index: 340075 (The Pile)

Max Activating Token Index: 1011

Text #13

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1623. Min Act: -0.0000

Data Index: 188207 (The Pile)

Max Activating Token Index: 307

Text #14

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1565. Min Act: -0.0000

Data Index: 32979 (The Pile)

Max Activating Token Index: 64

Text #15

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1633. Min Act: -0.0000

Data Index: 1019395 (The Pile)

Max Activating Token Index: 735

Text #16

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1556. Min Act: -0.0000

Data Index: 95220 (The Pile)

Max Activating Token Index: 256

Text #17

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1538. Min Act: -0.0000

Data Index: 1755863 (The Pile)

Max Activating Token Index: 182

Text #18

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1582. Min Act: -0.0000

Data Index: 518765 (The Pile)

Max Activating Token Index: 353

Text #19

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1566. Min Act: -0.0000

Data Index: 165864 (The Pile)

Max Activating Token Index: 422