Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 854 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2893. Min Act: -0.0001

Data Index: 1031208 (The Pile)

Max Activating Token Index: 655

Text #1

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2959. Min Act: -0.0000

Data Index: 615929 (The Pile)

Max Activating Token Index: 961

Text #2

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2462. Min Act: -0.0000

Data Index: 1834234 (The Pile)

Max Activating Token Index: 340

Text #3

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2239. Min Act: 0.0000

Data Index: 1245806 (The Pile)

Max Activating Token Index: 558

Text #4

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2318. Min Act: -0.0000

Data Index: 1425342 (The Pile)

Max Activating Token Index: 473

Text #5

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2306. Min Act: 0.0000

Data Index: 220351 (The Pile)

Max Activating Token Index: 607

Text #6

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2312. Min Act: -0.0000

Data Index: 194962 (The Pile)

Max Activating Token Index: 542

Text #7

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2021. Min Act: -0.0000

Data Index: 627235 (The Pile)

Max Activating Token Index: 728

Text #8

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2068. Min Act: -0.0000

Data Index: 1154300 (The Pile)

Max Activating Token Index: 562

Text #9

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.1992. Min Act: -0.0000

Data Index: 1371544 (The Pile)

Max Activating Token Index: 549

Text #10

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.1966. Min Act: -0.0000

Data Index: 1157205 (The Pile)

Max Activating Token Index: 189

Text #11

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.1905. Min Act: -0.0000

Data Index: 1194069 (The Pile)

Max Activating Token Index: 113

Text #12

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2025. Min Act: 0.0000

Data Index: 593039 (The Pile)

Max Activating Token Index: 992

Text #13

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2010. Min Act: -0.0000

Data Index: 1553030 (The Pile)

Max Activating Token Index: 915

Text #14

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2117. Min Act: -0.0000

Data Index: 949502 (The Pile)

Max Activating Token Index: 975

Text #15

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.1706. Min Act: -0.0000

Data Index: 787927 (The Pile)

Max Activating Token Index: 635

Text #16

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.1768. Min Act: -0.0000

Data Index: 240256 (The Pile)

Max Activating Token Index: 890

Text #17

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.1538. Min Act: -0.0000

Data Index: 1518259 (The Pile)

Max Activating Token Index: 829

Text #18

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.1636. Min Act: -0.0000

Data Index: 708185 (The Pile)

Max Activating Token Index: 307

Text #19

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.1751. Min Act: -0.0000

Data Index: 1091428 (The Pile)

Max Activating Token Index: 261