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

Dataset: The Pile

Neuron 1081 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: 0.1039. Min Range: -0.1039

Max Act: 0.1039. Min Act: -0.0000

Data Index: 1492637 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0999. Min Act: -0.0000

Data Index: 156765 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0991. Min Act: -0.0000

Data Index: 777192 (The Pile)

Max Activating Token Index: 82

Text #3

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0961. Min Act: -0.0000

Data Index: 656255 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0954. Min Act: -0.0000

Data Index: 1710355 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0933. Min Act: -0.0000

Data Index: 1419231 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0927. Min Act: -0.0000

Data Index: 915779 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0919. Min Act: -0.0000

Data Index: 350100 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0903. Min Act: -0.0000

Data Index: 1979162 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0899. Min Act: -0.0000

Data Index: 1244639 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0896. Min Act: -0.0000

Data Index: 184637 (The Pile)

Max Activating Token Index: 39

Text #11

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0895. Min Act: -0.0000

Data Index: 1774011 (The Pile)

Max Activating Token Index: 82

Text #12

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0923. Min Act: -0.0000

Data Index: 1771473 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0848. Min Act: -0.0000

Data Index: 1689092 (The Pile)

Max Activating Token Index: 590

Text #14

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0866. Min Act: -0.0000

Data Index: 1957319 (The Pile)

Max Activating Token Index: 131

Text #15

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0860. Min Act: -0.0000

Data Index: 881915 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0826. Min Act: -0.0000

Data Index: 1902417 (The Pile)

Max Activating Token Index: 100

Text #17

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0853. Min Act: -0.0000

Data Index: 1488306 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0848. Min Act: -0.0000

Data Index: 1640755 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0875. Min Act: -0.0000

Data Index: 1773791 (The Pile)

Max Activating Token Index: 1023