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

Dataset: The Pile

Neuron 3658 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: 0.0015. Min Range: -0.0015

Max Act: 0.0015. Min Act: -0.0000

Data Index: 1837012 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0014. Min Act: -0.0000

Data Index: 642170 (The Pile)

Max Activating Token Index: 1022

Text #2

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0014. Min Act: -0.0000

Data Index: 853557 (The Pile)

Max Activating Token Index: 932

Text #3

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0014. Min Act: -0.0000

Data Index: 980147 (The Pile)

Max Activating Token Index: 924

Text #4

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0013. Min Act: -0.0000

Data Index: 1181791 (The Pile)

Max Activating Token Index: 934

Text #5

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0013. Min Act: -0.0000

Data Index: 1868645 (The Pile)

Max Activating Token Index: 899

Text #6

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0013. Min Act: -0.0000

Data Index: 1691450 (The Pile)

Max Activating Token Index: 957

Text #7

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0012. Min Act: -0.0000

Data Index: 493067 (The Pile)

Max Activating Token Index: 765

Text #8

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0012. Min Act: -0.0000

Data Index: 1062964 (The Pile)

Max Activating Token Index: 993

Text #9

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0012. Min Act: -0.0000

Data Index: 1414544 (The Pile)

Max Activating Token Index: 897

Text #10

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0012. Min Act: -0.0000

Data Index: 1353908 (The Pile)

Max Activating Token Index: 953

Text #11

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0012. Min Act: -0.0000

Data Index: 1658863 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0012. Min Act: -0.0000

Data Index: 1555794 (The Pile)

Max Activating Token Index: 1001

Text #13

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0012. Min Act: -0.0000

Data Index: 1092613 (The Pile)

Max Activating Token Index: 962

Text #14

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0012. Min Act: -0.0000

Data Index: 1598385 (The Pile)

Max Activating Token Index: 995

Text #15

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0012. Min Act: -0.0000

Data Index: 1911358 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0012. Min Act: -0.0000

Data Index: 1642200 (The Pile)

Max Activating Token Index: 24

Text #17

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0011. Min Act: -0.0000

Data Index: 391155 (The Pile)

Max Activating Token Index: 955

Text #18

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0012. Min Act: -0.0000

Data Index: 511451 (The Pile)

Max Activating Token Index: 812

Text #19

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0011. Min Act: -0.0000

Data Index: 359833 (The Pile)

Max Activating Token Index: 968