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

Dataset: The Pile

Neuron 13 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.1042. Min Act: -0.0000

Data Index: 174398 (The Pile)

Max Activating Token Index: 710

Text #1

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.1002. Min Act: -0.0000

Data Index: 853009 (The Pile)

Max Activating Token Index: 142

Text #2

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.1014. Min Act: -0.0000

Data Index: 1031365 (The Pile)

Max Activating Token Index: 122

Text #3

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.1006. Min Act: -0.0000

Data Index: 659907 (The Pile)

Max Activating Token Index: 503

Text #4

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0999. Min Act: -0.0000

Data Index: 774375 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0857. Min Act: -0.0000

Data Index: 834126 (The Pile)

Max Activating Token Index: 217

Text #6

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.1011. Min Act: -0.0000

Data Index: 1291488 (The Pile)

Max Activating Token Index: 192

Text #7

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0898. Min Act: -0.0000

Data Index: 510270 (The Pile)

Max Activating Token Index: 32

Text #8

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0855. Min Act: -0.0000

Data Index: 1790352 (The Pile)

Max Activating Token Index: 830

Text #9

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0970. Min Act: -0.0000

Data Index: 490645 (The Pile)

Max Activating Token Index: 987

Text #10

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0925. Min Act: -0.0000

Data Index: 1320995 (The Pile)

Max Activating Token Index: 333

Text #11

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0817. Min Act: -0.0000

Data Index: 994816 (The Pile)

Max Activating Token Index: 115

Text #12

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0861. Min Act: -0.0000

Data Index: 1730298 (The Pile)

Max Activating Token Index: 516

Text #13

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0886. Min Act: -0.0000

Data Index: 1608471 (The Pile)

Max Activating Token Index: 126

Text #14

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0835. Min Act: -0.0000

Data Index: 239486 (The Pile)

Max Activating Token Index: 477

Text #15

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0755. Min Act: -0.0000

Data Index: 738851 (The Pile)

Max Activating Token Index: 932

Text #16

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0857. Min Act: -0.0000

Data Index: 1966464 (The Pile)

Max Activating Token Index: 185

Text #17

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0816. Min Act: -0.0000

Data Index: 1829217 (The Pile)

Max Activating Token Index: 330

Text #18

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0819. Min Act: -0.0000

Data Index: 824985 (The Pile)

Max Activating Token Index: 524

Text #19

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0813. Min Act: -0.0000

Data Index: 178263 (The Pile)

Max Activating Token Index: 141