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

Dataset: The Pile

Neuron 900 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: 0.1360. Min Range: -0.1360

Max Act: 0.1360. Min Act: -0.0000

Data Index: 1691828 (The Pile)

Max Activating Token Index: 763

Text #1

Max Range: 0.1360. Min Range: -0.1360

Max Act: 0.1142. Min Act: -0.0000

Data Index: 1432044 (The Pile)

Max Activating Token Index: 351

Text #2

Max Range: 0.1360. Min Range: -0.1360

Max Act: 0.1111. Min Act: 0.0000

Data Index: 279807 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1360. Min Range: -0.1360

Max Act: 0.1070. Min Act: 0.0000

Data Index: 321144 (The Pile)

Max Activating Token Index: 78

Text #4

Max Range: 0.1360. Min Range: -0.1360

Max Act: 0.1038. Min Act: -0.0000

Data Index: 1301148 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1360. Min Range: -0.1360

Max Act: 0.1035. Min Act: 0.0000

Data Index: 1921913 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1360. Min Range: -0.1360

Max Act: 0.1031. Min Act: -0.0000

Data Index: 1523153 (The Pile)

Max Activating Token Index: 234

Text #7

Max Range: 0.1360. Min Range: -0.1360

Max Act: 0.1025. Min Act: -0.0000

Data Index: 1263793 (The Pile)

Max Activating Token Index: 56

Text #8

Max Range: 0.1360. Min Range: -0.1360

Max Act: 0.1021. Min Act: 0.0000

Data Index: 390753 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1360. Min Range: -0.1360

Max Act: 0.0994. Min Act: 0.0000

Data Index: 1172654 (The Pile)

Max Activating Token Index: 910

Text #10

Max Range: 0.1360. Min Range: -0.1360

Max Act: 0.0986. Min Act: -0.0000

Data Index: 1609683 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1360. Min Range: -0.1360

Max Act: 0.0987. Min Act: -0.0000

Data Index: 1650291 (The Pile)

Max Activating Token Index: 12

Text #12

Max Range: 0.1360. Min Range: -0.1360

Max Act: 0.0983. Min Act: -0.0000

Data Index: 217529 (The Pile)

Max Activating Token Index: 12

Text #13

Max Range: 0.1360. Min Range: -0.1360

Max Act: 0.0983. Min Act: 0.0000

Data Index: 391808 (The Pile)

Max Activating Token Index: 600

Text #14

Max Range: 0.1360. Min Range: -0.1360

Max Act: 0.1018. Min Act: -0.0000

Data Index: 997701 (The Pile)

Max Activating Token Index: 1018

Text #15

Max Range: 0.1360. Min Range: -0.1360

Max Act: 0.0980. Min Act: 0.0000

Data Index: 1213207 (The Pile)

Max Activating Token Index: 68

Text #16

Max Range: 0.1360. Min Range: -0.1360

Max Act: 0.0975. Min Act: -0.0000

Data Index: 1658303 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1360. Min Range: -0.1360

Max Act: 0.0972. Min Act: -0.0000

Data Index: 1635123 (The Pile)

Max Activating Token Index: 971

Text #18

Max Range: 0.1360. Min Range: -0.1360

Max Act: 0.1006. Min Act: -0.0000

Data Index: 1601891 (The Pile)

Max Activating Token Index: 293

Text #19

Max Range: 0.1360. Min Range: -0.1360

Max Act: 0.0972. Min Act: 0.0000

Data Index: 779917 (The Pile)

Max Activating Token Index: 599