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

Dataset: The Pile

Neuron 904 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: 0.2259. Min Range: -0.2259

Max Act: 0.2215. Min Act: -0.0000

Data Index: 1435677 (The Pile)

Max Activating Token Index: 579

Text #1

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1966. Min Act: -0.0000

Data Index: 1934600 (The Pile)

Max Activating Token Index: 531

Text #2

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.2259. Min Act: -0.0000

Data Index: 44214 (The Pile)

Max Activating Token Index: 591

Text #3

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.2150. Min Act: -0.0000

Data Index: 1011126 (The Pile)

Max Activating Token Index: 400

Text #4

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.2022. Min Act: -0.0000

Data Index: 982023 (The Pile)

Max Activating Token Index: 995

Text #5

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.2026. Min Act: -0.0000

Data Index: 330606 (The Pile)

Max Activating Token Index: 258

Text #6

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.2144. Min Act: -0.0000

Data Index: 899967 (The Pile)

Max Activating Token Index: 554

Text #7

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.2015. Min Act: -0.0000

Data Index: 1252771 (The Pile)

Max Activating Token Index: 766

Text #8

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.2034. Min Act: -0.0000

Data Index: 785689 (The Pile)

Max Activating Token Index: 251

Text #9

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1891. Min Act: -0.0000

Data Index: 1697733 (The Pile)

Max Activating Token Index: 818

Text #10

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1903. Min Act: -0.0000

Data Index: 627128 (The Pile)

Max Activating Token Index: 70

Text #11

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1844. Min Act: -0.0000

Data Index: 891946 (The Pile)

Max Activating Token Index: 305

Text #12

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1826. Min Act: -0.0000

Data Index: 1655121 (The Pile)

Max Activating Token Index: 497

Text #13

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1885. Min Act: -0.0000

Data Index: 435320 (The Pile)

Max Activating Token Index: 197

Text #14

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1723. Min Act: -0.0000

Data Index: 1892401 (The Pile)

Max Activating Token Index: 732

Text #15

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.2054. Min Act: -0.0000

Data Index: 894648 (The Pile)

Max Activating Token Index: 651

Text #16

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1712. Min Act: -0.0000

Data Index: 316950 (The Pile)

Max Activating Token Index: 916

Text #17

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1713. Min Act: -0.0000

Data Index: 1289460 (The Pile)

Max Activating Token Index: 790

Text #18

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1685. Min Act: -0.0000

Data Index: 547918 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1917. Min Act: -0.0000

Data Index: 1991443 (The Pile)

Max Activating Token Index: 51