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

Dataset: The Pile

Neuron 1118 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: 0.1047. Min Range: -0.1047

Max Act: 0.1047. Min Act: 0.0000

Data Index: 1893671 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.1037. Min Act: 0.0000

Data Index: 1479331 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.1024. Min Act: 0.0000

Data Index: 11329 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.1024. Min Act: 0.0000

Data Index: 1011385 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.1018. Min Act: 0.0000

Data Index: 153339 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.1016. Min Act: 0.0000

Data Index: 1953831 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.1011. Min Act: 0.0000

Data Index: 456620 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.1010. Min Act: 0.0000

Data Index: 1700085 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0998. Min Act: 0.0000

Data Index: 824051 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0998. Min Act: 0.0000

Data Index: 1725610 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0993. Min Act: 0.0000

Data Index: 1667505 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0991. Min Act: 0.0000

Data Index: 1316706 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0988. Min Act: 0.0000

Data Index: 1435526 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0987. Min Act: 0.0000

Data Index: 867561 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0982. Min Act: 0.0000

Data Index: 1089672 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0978. Min Act: 0.0000

Data Index: 172507 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0973. Min Act: 0.0000

Data Index: 493322 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0974. Min Act: 0.0000

Data Index: 1695701 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0975. Min Act: 0.0000

Data Index: 436081 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0966. Min Act: 0.0000

Data Index: 385642 (The Pile)

Max Activating Token Index: 1023