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

Dataset: The Pile

Neuron 2791 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: 0.3192. Min Range: -0.3192

Max Act: 0.3192. Min Act: -0.0000

Data Index: 1157337 (The Pile)

Max Activating Token Index: 119

Text #1

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2706. Min Act: -0.0000

Data Index: 727553 (The Pile)

Max Activating Token Index: 415

Text #2

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2590. Min Act: -0.0000

Data Index: 849586 (The Pile)

Max Activating Token Index: 537

Text #3

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2586. Min Act: -0.0000

Data Index: 1252915 (The Pile)

Max Activating Token Index: 819

Text #4

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2311. Min Act: -0.0000

Data Index: 1274403 (The Pile)

Max Activating Token Index: 292

Text #5

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2467. Min Act: -0.0000

Data Index: 1132792 (The Pile)

Max Activating Token Index: 379

Text #6

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2490. Min Act: -0.0000

Data Index: 1736844 (The Pile)

Max Activating Token Index: 123

Text #7

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2531. Min Act: -0.0000

Data Index: 1359889 (The Pile)

Max Activating Token Index: 175

Text #8

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2360. Min Act: -0.0000

Data Index: 1049855 (The Pile)

Max Activating Token Index: 638

Text #9

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2517. Min Act: -0.0000

Data Index: 1209984 (The Pile)

Max Activating Token Index: 902

Text #10

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2034. Min Act: -0.0000

Data Index: 874076 (The Pile)

Max Activating Token Index: 810

Text #11

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.1936. Min Act: -0.0000

Data Index: 1952929 (The Pile)

Max Activating Token Index: 832

Text #12

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2058. Min Act: -0.0000

Data Index: 1783046 (The Pile)

Max Activating Token Index: 286

Text #13

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.1847. Min Act: -0.0000

Data Index: 396894 (The Pile)

Max Activating Token Index: 915

Text #14

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2107. Min Act: -0.0000

Data Index: 1594292 (The Pile)

Max Activating Token Index: 111

Text #15

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.1886. Min Act: -0.0000

Data Index: 75737 (The Pile)

Max Activating Token Index: 742

Text #16

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.1699. Min Act: -0.0000

Data Index: 1727636 (The Pile)

Max Activating Token Index: 446

Text #17

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.1935. Min Act: -0.0000

Data Index: 473905 (The Pile)

Max Activating Token Index: 215

Text #18

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.1878. Min Act: -0.0000

Data Index: 501949 (The Pile)

Max Activating Token Index: 861

Text #19

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.1715. Min Act: -0.0000

Data Index: 1322201 (The Pile)

Max Activating Token Index: 127