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

Dataset: The Pile

Neuron 2221 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: 0.1023. Min Range: -0.1023

Max Act: 0.1023. Min Act: -0.0000

Data Index: 1345799 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.1013. Min Act: -0.0000

Data Index: 1658801 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0981. Min Act: -0.0000

Data Index: 1372124 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0967. Min Act: -0.0000

Data Index: 1752441 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0957. Min Act: -0.0000

Data Index: 915320 (The Pile)

Max Activating Token Index: 1

Text #5

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0957. Min Act: -0.0000

Data Index: 1070393 (The Pile)

Max Activating Token Index: 1

Text #6

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0957. Min Act: -0.0000

Data Index: 634961 (The Pile)

Max Activating Token Index: 1

Text #7

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0957. Min Act: -0.0000

Data Index: 1680141 (The Pile)

Max Activating Token Index: 1

Text #8

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0957. Min Act: -0.0000

Data Index: 1340791 (The Pile)

Max Activating Token Index: 1

Text #9

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0957. Min Act: -0.0000

Data Index: 592107 (The Pile)

Max Activating Token Index: 1

Text #10

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0957. Min Act: -0.0000

Data Index: 1046136 (The Pile)

Max Activating Token Index: 1

Text #11

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0957. Min Act: -0.0000

Data Index: 162534 (The Pile)

Max Activating Token Index: 1

Text #12

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0957. Min Act: -0.0000

Data Index: 835987 (The Pile)

Max Activating Token Index: 1

Text #13

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0957. Min Act: -0.0000

Data Index: 11431 (The Pile)

Max Activating Token Index: 1

Text #14

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0957. Min Act: -0.0000

Data Index: 498161 (The Pile)

Max Activating Token Index: 1

Text #15

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0957. Min Act: -0.0000

Data Index: 1894407 (The Pile)

Max Activating Token Index: 1

Text #16

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0955. Min Act: -0.0000

Data Index: 1958454 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0948. Min Act: -0.0000

Data Index: 191929 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0946. Min Act: -0.0000

Data Index: 1665594 (The Pile)

Max Activating Token Index: 2

Text #19

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0944. Min Act: -0.0000

Data Index: 416707 (The Pile)

Max Activating Token Index: 1023