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

Dataset: The Pile

Neuron 3336 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2608. Min Act: -0.0000

Data Index: 198073 (The Pile)

Max Activating Token Index: 642

Text #1

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2280. Min Act: -0.0001

Data Index: 1796531 (The Pile)

Max Activating Token Index: 167

Text #2

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2216. Min Act: -0.0000

Data Index: 203836 (The Pile)

Max Activating Token Index: 178

Text #3

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2228. Min Act: -0.0000

Data Index: 63445 (The Pile)

Max Activating Token Index: 189

Text #4

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2018. Min Act: -0.0000

Data Index: 1366447 (The Pile)

Max Activating Token Index: 225

Text #5

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2061. Min Act: -0.0000

Data Index: 890120 (The Pile)

Max Activating Token Index: 333

Text #6

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.1924. Min Act: -0.0000

Data Index: 99767 (The Pile)

Max Activating Token Index: 172

Text #7

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.1926. Min Act: -0.0000

Data Index: 1733749 (The Pile)

Max Activating Token Index: 836

Text #8

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2065. Min Act: -0.0000

Data Index: 1468052 (The Pile)

Max Activating Token Index: 806

Text #9

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.1906. Min Act: -0.0000

Data Index: 1200859 (The Pile)

Max Activating Token Index: 405

Text #10

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.1917. Min Act: -0.0000

Data Index: 668913 (The Pile)

Max Activating Token Index: 540

Text #11

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.1965. Min Act: -0.0000

Data Index: 270870 (The Pile)

Max Activating Token Index: 849

Text #12

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2060. Min Act: -0.0000

Data Index: 1917887 (The Pile)

Max Activating Token Index: 1005

Text #13

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.1906. Min Act: -0.0000

Data Index: 454578 (The Pile)

Max Activating Token Index: 872

Text #14

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.1810. Min Act: -0.0000

Data Index: 98908 (The Pile)

Max Activating Token Index: 40

Text #15

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.1918. Min Act: -0.0000

Data Index: 963205 (The Pile)

Max Activating Token Index: 642

Text #16

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.1865. Min Act: -0.0000

Data Index: 1257351 (The Pile)

Max Activating Token Index: 747

Text #17

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.1765. Min Act: -0.0000

Data Index: 1562079 (The Pile)

Max Activating Token Index: 66

Text #18

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.1766. Min Act: -0.0000

Data Index: 1892536 (The Pile)

Max Activating Token Index: 592

Text #19

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2007. Min Act: -0.0000

Data Index: 267461 (The Pile)

Max Activating Token Index: 251