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

Dataset: The Pile

Neuron 4363 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2578. Min Act: -0.0000

Data Index: 1996905 (The Pile)

Max Activating Token Index: 800

Text #1

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2414. Min Act: -0.0000

Data Index: 1540385 (The Pile)

Max Activating Token Index: 111

Text #2

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2198. Min Act: -0.0000

Data Index: 912732 (The Pile)

Max Activating Token Index: 18

Text #3

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2428. Min Act: -0.0000

Data Index: 1437711 (The Pile)

Max Activating Token Index: 854

Text #4

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2178. Min Act: -0.0000

Data Index: 559237 (The Pile)

Max Activating Token Index: 18

Text #5

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2290. Min Act: -0.0000

Data Index: 721097 (The Pile)

Max Activating Token Index: 25

Text #6

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2079. Min Act: -0.0000

Data Index: 1886529 (The Pile)

Max Activating Token Index: 677

Text #7

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.1977. Min Act: -0.0000

Data Index: 1887189 (The Pile)

Max Activating Token Index: 40

Text #8

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.1884. Min Act: -0.0000

Data Index: 1090634 (The Pile)

Max Activating Token Index: 15

Text #9

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2164. Min Act: -0.0000

Data Index: 628417 (The Pile)

Max Activating Token Index: 118

Text #10

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2131. Min Act: -0.0000

Data Index: 44465 (The Pile)

Max Activating Token Index: 226

Text #11

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.1930. Min Act: -0.0000

Data Index: 491868 (The Pile)

Max Activating Token Index: 56

Text #12

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.1987. Min Act: -0.0000

Data Index: 1514155 (The Pile)

Max Activating Token Index: 31

Text #13

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.1930. Min Act: -0.0000

Data Index: 429812 (The Pile)

Max Activating Token Index: 155

Text #14

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.1941. Min Act: -0.0000

Data Index: 1221143 (The Pile)

Max Activating Token Index: 44

Text #15

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.1796. Min Act: -0.0000

Data Index: 938033 (The Pile)

Max Activating Token Index: 678

Text #16

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.1858. Min Act: -0.0000

Data Index: 1887914 (The Pile)

Max Activating Token Index: 176

Text #17

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.1993. Min Act: -0.0000

Data Index: 1636483 (The Pile)

Max Activating Token Index: 44

Text #18

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.1835. Min Act: -0.0000

Data Index: 832262 (The Pile)

Max Activating Token Index: 561

Text #19

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.1770. Min Act: -0.0000

Data Index: 1103523 (The Pile)

Max Activating Token Index: 244