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

Dataset: The Pile

Neuron 2871 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: 0.1025. Min Range: -0.1025

Max Act: 0.1025. Min Act: -0.0000

Data Index: 169655 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.1013. Min Act: -0.0000

Data Index: 1763063 (The Pile)

Max Activating Token Index: 123

Text #2

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.1006. Min Act: -0.0000

Data Index: 939252 (The Pile)

Max Activating Token Index: 15

Text #3

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0991. Min Act: -0.0000

Data Index: 1037603 (The Pile)

Max Activating Token Index: 626

Text #4

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0983. Min Act: -0.0000

Data Index: 392134 (The Pile)

Max Activating Token Index: 542

Text #5

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0985. Min Act: 0.0000

Data Index: 1016776 (The Pile)

Max Activating Token Index: 193

Text #6

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.1013. Min Act: -0.0000

Data Index: 1504829 (The Pile)

Max Activating Token Index: 976

Text #7

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0972. Min Act: -0.0000

Data Index: 1953599 (The Pile)

Max Activating Token Index: 113

Text #8

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0968. Min Act: 0.0000

Data Index: 1135930 (The Pile)

Max Activating Token Index: 28

Text #9

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0966. Min Act: -0.0000

Data Index: 725654 (The Pile)

Max Activating Token Index: 172

Text #10

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0958. Min Act: -0.0000

Data Index: 706957 (The Pile)

Max Activating Token Index: 163

Text #11

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0958. Min Act: -0.0000

Data Index: 1108658 (The Pile)

Max Activating Token Index: 136

Text #12

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0958. Min Act: -0.0000

Data Index: 1782011 (The Pile)

Max Activating Token Index: 49

Text #13

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0956. Min Act: -0.0000

Data Index: 672024 (The Pile)

Max Activating Token Index: 630

Text #14

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0921. Min Act: -0.0000

Data Index: 258259 (The Pile)

Max Activating Token Index: 55

Text #15

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0952. Min Act: -0.0000

Data Index: 38917 (The Pile)

Max Activating Token Index: 31

Text #16

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0987. Min Act: -0.0000

Data Index: 1061961 (The Pile)

Max Activating Token Index: 641

Text #17

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0954. Min Act: -0.0000

Data Index: 561530 (The Pile)

Max Activating Token Index: 723

Text #18

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0950. Min Act: -0.0000

Data Index: 943963 (The Pile)

Max Activating Token Index: 365

Text #19

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0948. Min Act: -0.0000

Data Index: 484885 (The Pile)

Max Activating Token Index: 101