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

Dataset: The Pile

Neuron 3683 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: 0.1198. Min Range: -0.1198

Max Act: 0.1198. Min Act: 0.0000

Data Index: 944829 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1145. Min Act: -0.0000

Data Index: 339882 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1057. Min Act: 0.0000

Data Index: 281640 (The Pile)

Max Activating Token Index: 906

Text #3

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1057. Min Act: -0.0000

Data Index: 772134 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1034. Min Act: 0.0000

Data Index: 1724182 (The Pile)

Max Activating Token Index: 956

Text #5

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1033. Min Act: -0.0000

Data Index: 1480289 (The Pile)

Max Activating Token Index: 19

Text #6

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1022. Min Act: -0.0000

Data Index: 393426 (The Pile)

Max Activating Token Index: 1011

Text #7

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1010. Min Act: -0.0000

Data Index: 1516226 (The Pile)

Max Activating Token Index: 839

Text #8

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1003. Min Act: -0.0000

Data Index: 134421 (The Pile)

Max Activating Token Index: 138

Text #9

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0976. Min Act: -0.0000

Data Index: 1206442 (The Pile)

Max Activating Token Index: 483

Text #10

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1002. Min Act: -0.0000

Data Index: 501118 (The Pile)

Max Activating Token Index: 646

Text #11

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0965. Min Act: 0.0000

Data Index: 844483 (The Pile)

Max Activating Token Index: 255

Text #12

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0965. Min Act: 0.0000

Data Index: 330356 (The Pile)

Max Activating Token Index: 1011

Text #13

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0951. Min Act: -0.0000

Data Index: 1909640 (The Pile)

Max Activating Token Index: 129

Text #14

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0936. Min Act: 0.0000

Data Index: 62549 (The Pile)

Max Activating Token Index: 92

Text #15

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0937. Min Act: 0.0000

Data Index: 78338 (The Pile)

Max Activating Token Index: 382

Text #16

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0921. Min Act: -0.0000

Data Index: 1348761 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0919. Min Act: -0.0000

Data Index: 1035839 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0917. Min Act: 0.0000

Data Index: 1985335 (The Pile)

Max Activating Token Index: 770

Text #19

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0883. Min Act: 0.0000

Data Index: 503885 (The Pile)

Max Activating Token Index: 1023