Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 922 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.2847. Min Act: -0.0000

Data Index: 479900 (The Pile)

Max Activating Token Index: 685

Text #1

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.2398. Min Act: -0.0000

Data Index: 707727 (The Pile)

Max Activating Token Index: 53

Text #2

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.2739. Min Act: -0.0000

Data Index: 1140681 (The Pile)

Max Activating Token Index: 711

Text #3

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.2255. Min Act: -0.0000

Data Index: 286910 (The Pile)

Max Activating Token Index: 355

Text #4

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.2137. Min Act: -0.0000

Data Index: 1964485 (The Pile)

Max Activating Token Index: 956

Text #5

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.2122. Min Act: -0.0000

Data Index: 1155890 (The Pile)

Max Activating Token Index: 169

Text #6

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.2188. Min Act: -0.0000

Data Index: 1548550 (The Pile)

Max Activating Token Index: 548

Text #7

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.2164. Min Act: -0.0000

Data Index: 1995416 (The Pile)

Max Activating Token Index: 856

Text #8

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.2115. Min Act: -0.0000

Data Index: 789162 (The Pile)

Max Activating Token Index: 754

Text #9

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.2058. Min Act: -0.0000

Data Index: 1955605 (The Pile)

Max Activating Token Index: 119

Text #10

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.1918. Min Act: -0.0000

Data Index: 1853795 (The Pile)

Max Activating Token Index: 106

Text #11

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.2276. Min Act: -0.0000

Data Index: 607067 (The Pile)

Max Activating Token Index: 919

Text #12

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.1857. Min Act: -0.0000

Data Index: 1243692 (The Pile)

Max Activating Token Index: 736

Text #13

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.1910. Min Act: -0.0000

Data Index: 768840 (The Pile)

Max Activating Token Index: 235

Text #14

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.1887. Min Act: -0.0000

Data Index: 1571926 (The Pile)

Max Activating Token Index: 715

Text #15

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.2075. Min Act: -0.0000

Data Index: 1985796 (The Pile)

Max Activating Token Index: 622

Text #16

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.1856. Min Act: -0.0000

Data Index: 149636 (The Pile)

Max Activating Token Index: 151

Text #17

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.2119. Min Act: -0.0000

Data Index: 898662 (The Pile)

Max Activating Token Index: 691

Text #18

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.1841. Min Act: -0.0000

Data Index: 1632682 (The Pile)

Max Activating Token Index: 477

Text #19

Max Range: 0.2847. Min Range: -0.2847

Max Act: 0.1814. Min Act: -0.0000

Data Index: 63677 (The Pile)

Max Activating Token Index: 341