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

Dataset: The Pile

Neuron 1953 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.1074. Min Act: 0.0000

Data Index: 128564 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.1072. Min Act: 0.0000

Data Index: 1391474 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.1065. Min Act: 0.0000

Data Index: 394319 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.1057. Min Act: 0.0000

Data Index: 1512052 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.1055. Min Act: -0.0000

Data Index: 734581 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.1041. Min Act: -0.0000

Data Index: 1836189 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.1036. Min Act: -0.0000

Data Index: 1132024 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.1031. Min Act: -0.0000

Data Index: 575247 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.1031. Min Act: -0.0000

Data Index: 1770176 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0990. Min Act: -0.0000

Data Index: 613550 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.1026. Min Act: 0.0000

Data Index: 1350902 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.1024. Min Act: 0.0000

Data Index: 1842503 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.1025. Min Act: -0.0000

Data Index: 254334 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.1023. Min Act: 0.0000

Data Index: 1280691 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.1023. Min Act: 0.0000

Data Index: 1707526 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0984. Min Act: -0.0000

Data Index: 389432 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.1020. Min Act: -0.0000

Data Index: 551406 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.1020. Min Act: -0.0000

Data Index: 1768768 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0981. Min Act: 0.0000

Data Index: 1587411 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.1012. Min Act: -0.0000

Data Index: 752258 (The Pile)

Max Activating Token Index: 1023