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

Dataset: The Pile

Neuron 1337 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: 0.2725. Min Range: -0.2725

Max Act: 0.2725. Min Act: -0.0000

Data Index: 1662320 (The Pile)

Max Activating Token Index: 764

Text #1

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.2368. Min Act: -0.0000

Data Index: 232918 (The Pile)

Max Activating Token Index: 994

Text #2

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.2284. Min Act: -0.0000

Data Index: 1847661 (The Pile)

Max Activating Token Index: 557

Text #3

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.2487. Min Act: -0.0000

Data Index: 359605 (The Pile)

Max Activating Token Index: 987

Text #4

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.2104. Min Act: -0.0000

Data Index: 1927791 (The Pile)

Max Activating Token Index: 812

Text #5

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.2146. Min Act: -0.0000

Data Index: 1515488 (The Pile)

Max Activating Token Index: 404

Text #6

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.2193. Min Act: -0.0000

Data Index: 1460414 (The Pile)

Max Activating Token Index: 695

Text #7

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.2162. Min Act: -0.0000

Data Index: 1501828 (The Pile)

Max Activating Token Index: 949

Text #8

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1999. Min Act: -0.0000

Data Index: 623908 (The Pile)

Max Activating Token Index: 614

Text #9

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1973. Min Act: -0.0000

Data Index: 309780 (The Pile)

Max Activating Token Index: 953

Text #10

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.2109. Min Act: -0.0000

Data Index: 1573178 (The Pile)

Max Activating Token Index: 60

Text #11

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1995. Min Act: -0.0000

Data Index: 392359 (The Pile)

Max Activating Token Index: 893

Text #12

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1999. Min Act: -0.0000

Data Index: 849587 (The Pile)

Max Activating Token Index: 699

Text #13

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1980. Min Act: -0.0000

Data Index: 357395 (The Pile)

Max Activating Token Index: 618

Text #14

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1921. Min Act: -0.0000

Data Index: 1015503 (The Pile)

Max Activating Token Index: 410

Text #15

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1935. Min Act: -0.0000

Data Index: 402034 (The Pile)

Max Activating Token Index: 902

Text #16

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1871. Min Act: -0.0000

Data Index: 37833 (The Pile)

Max Activating Token Index: 948

Text #17

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1922. Min Act: -0.0000

Data Index: 1276504 (The Pile)

Max Activating Token Index: 781

Text #18

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.2006. Min Act: -0.0000

Data Index: 1154537 (The Pile)

Max Activating Token Index: 813

Text #19

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1931. Min Act: -0.0000

Data Index: 935663 (The Pile)

Max Activating Token Index: 163