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

Dataset: The Pile

Neuron 4530 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: 0.1149. Min Range: -0.1149

Max Act: 0.1149. Min Act: -0.0000

Data Index: 215477 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.1148. Min Act: -0.0000

Data Index: 816657 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.1110. Min Act: -0.0000

Data Index: 1834124 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.1084. Min Act: 0.0000

Data Index: 1479658 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.1074. Min Act: -0.0000

Data Index: 1472463 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.1067. Min Act: -0.0000

Data Index: 21635 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.1061. Min Act: 0.0000

Data Index: 1855088 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.1047. Min Act: -0.0000

Data Index: 1845539 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.1034. Min Act: 0.0000

Data Index: 1704527 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.1029. Min Act: -0.0000

Data Index: 19448 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.1025. Min Act: -0.0000

Data Index: 977255 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.1020. Min Act: -0.0000

Data Index: 1215 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.1004. Min Act: -0.0000

Data Index: 1457902 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0988. Min Act: -0.0000

Data Index: 1442010 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0986. Min Act: -0.0000

Data Index: 1646473 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0983. Min Act: 0.0000

Data Index: 658274 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0976. Min Act: -0.0000

Data Index: 1764913 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0971. Min Act: -0.0000

Data Index: 108288 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0965. Min Act: 0.0000

Data Index: 764765 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0959. Min Act: 0.0000

Data Index: 1386652 (The Pile)

Max Activating Token Index: 1023