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

Dataset: The Pile

Neuron 2580 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: 0.1164. Min Range: -0.1164

Max Act: 0.1142. Min Act: -0.0000

Data Index: 287828 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1139. Min Act: -0.0000

Data Index: 872494 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1164. Min Act: -0.0000

Data Index: 20572 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1103. Min Act: 0.0000

Data Index: 1503216 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1090. Min Act: -0.0000

Data Index: 1785366 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1083. Min Act: -0.0000

Data Index: 1370554 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1081. Min Act: 0.0000

Data Index: 1126001 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1107. Min Act: 0.0000

Data Index: 1127017 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1047. Min Act: -0.0000

Data Index: 400797 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1035. Min Act: -0.0000

Data Index: 440453 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1023. Min Act: -0.0000

Data Index: 1131298 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1020. Min Act: -0.0000

Data Index: 710946 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1018. Min Act: -0.0000

Data Index: 1247017 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1016. Min Act: 0.0000

Data Index: 1821454 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1053. Min Act: -0.0000

Data Index: 1928251 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1016. Min Act: 0.0000

Data Index: 1469119 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1013. Min Act: -0.0000

Data Index: 816653 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1007. Min Act: -0.0000

Data Index: 1546411 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0997. Min Act: 0.0000

Data Index: 923784 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1025. Min Act: 0.0000

Data Index: 1547264 (The Pile)

Max Activating Token Index: 1023