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

Dataset: The Pile

Neuron 3059 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: 0.1098. Min Range: -0.1098

Max Act: 0.1098. Min Act: -0.0000

Data Index: 1314351 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.1066. Min Act: -0.0000

Data Index: 1554947 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.1047. Min Act: -0.0000

Data Index: 1910563 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.1042. Min Act: -0.0000

Data Index: 1896276 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.1031. Min Act: -0.0000

Data Index: 1763235 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.1030. Min Act: -0.0000

Data Index: 1793738 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.1029. Min Act: -0.0000

Data Index: 1240046 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.1027. Min Act: -0.0000

Data Index: 1922918 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.1017. Min Act: 0.0000

Data Index: 1713456 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.1011. Min Act: -0.0000

Data Index: 981425 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.1004. Min Act: -0.0000

Data Index: 813945 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0997. Min Act: -0.0000

Data Index: 45931 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.1027. Min Act: -0.0000

Data Index: 685157 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0987. Min Act: -0.0000

Data Index: 1914926 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0984. Min Act: -0.0000

Data Index: 1711691 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0985. Min Act: -0.0000

Data Index: 778516 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0978. Min Act: -0.0000

Data Index: 1929183 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0974. Min Act: -0.0000

Data Index: 546823 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0972. Min Act: -0.0000

Data Index: 768668 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0974. Min Act: -0.0000

Data Index: 1048981 (The Pile)

Max Activating Token Index: 1023