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

Dataset: The Pile

Neuron 3568 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: 0.2928. Min Range: -0.2928

Max Act: 0.2928. Min Act: -0.0000

Data Index: 1416694 (The Pile)

Max Activating Token Index: 97

Text #1

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2337. Min Act: -0.0000

Data Index: 1211160 (The Pile)

Max Activating Token Index: 900

Text #2

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2015. Min Act: -0.0000

Data Index: 20529 (The Pile)

Max Activating Token Index: 768

Text #3

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2089. Min Act: -0.0000

Data Index: 269186 (The Pile)

Max Activating Token Index: 412

Text #4

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.1986. Min Act: -0.0000

Data Index: 1125459 (The Pile)

Max Activating Token Index: 210

Text #5

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2089. Min Act: -0.0000

Data Index: 843973 (The Pile)

Max Activating Token Index: 96

Text #6

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2040. Min Act: -0.0000

Data Index: 503149 (The Pile)

Max Activating Token Index: 167

Text #7

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2254. Min Act: -0.0000

Data Index: 451267 (The Pile)

Max Activating Token Index: 768

Text #8

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.1970. Min Act: -0.0000

Data Index: 1408159 (The Pile)

Max Activating Token Index: 742

Text #9

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.1979. Min Act: -0.0000

Data Index: 1533903 (The Pile)

Max Activating Token Index: 273

Text #10

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.1922. Min Act: -0.0000

Data Index: 860920 (The Pile)

Max Activating Token Index: 594

Text #11

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.1918. Min Act: -0.0000

Data Index: 1866562 (The Pile)

Max Activating Token Index: 961

Text #12

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.1839. Min Act: -0.0000

Data Index: 373777 (The Pile)

Max Activating Token Index: 188

Text #13

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.1651. Min Act: -0.0000

Data Index: 1645755 (The Pile)

Max Activating Token Index: 730

Text #14

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.1874. Min Act: -0.0000

Data Index: 1340498 (The Pile)

Max Activating Token Index: 306

Text #15

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.1812. Min Act: -0.0000

Data Index: 1833067 (The Pile)

Max Activating Token Index: 638

Text #16

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.1817. Min Act: -0.0000

Data Index: 163194 (The Pile)

Max Activating Token Index: 564

Text #17

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.1572. Min Act: -0.0000

Data Index: 1472097 (The Pile)

Max Activating Token Index: 955

Text #18

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2053. Min Act: -0.0000

Data Index: 1952982 (The Pile)

Max Activating Token Index: 89

Text #19

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.1845. Min Act: -0.0000

Data Index: 493773 (The Pile)

Max Activating Token Index: 507