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

Dataset: The Pile

Neuron 3940 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: 0.1224. Min Range: -0.1224

Max Act: 0.1224. Min Act: 0.0000

Data Index: 1730247 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1197. Min Act: -0.0000

Data Index: 797428 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1189. Min Act: 0.0000

Data Index: 648530 (The Pile)

Max Activating Token Index: 40

Text #3

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1138. Min Act: 0.0000

Data Index: 1964380 (The Pile)

Max Activating Token Index: 142

Text #4

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1105. Min Act: -0.0000

Data Index: 619721 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1105. Min Act: 0.0000

Data Index: 1527785 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1102. Min Act: -0.0000

Data Index: 1799376 (The Pile)

Max Activating Token Index: 26

Text #7

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1077. Min Act: 0.0000

Data Index: 232115 (The Pile)

Max Activating Token Index: 22

Text #8

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1074. Min Act: -0.0000

Data Index: 890580 (The Pile)

Max Activating Token Index: 41

Text #9

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1062. Min Act: 0.0000

Data Index: 1536350 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1062. Min Act: 0.0000

Data Index: 1817094 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1059. Min Act: -0.0000

Data Index: 1103414 (The Pile)

Max Activating Token Index: 11

Text #12

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1049. Min Act: 0.0000

Data Index: 161482 (The Pile)

Max Activating Token Index: 4

Text #13

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1039. Min Act: 0.0000

Data Index: 738874 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1072. Min Act: -0.0000

Data Index: 1421897 (The Pile)

Max Activating Token Index: 39

Text #15

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1029. Min Act: 0.0000

Data Index: 1165092 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1055. Min Act: 0.0000

Data Index: 514484 (The Pile)

Max Activating Token Index: 9

Text #17

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1014. Min Act: 0.0000

Data Index: 251813 (The Pile)

Max Activating Token Index: 7

Text #18

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1007. Min Act: -0.0000

Data Index: 1771617 (The Pile)

Max Activating Token Index: 9

Text #19

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0992. Min Act: 0.0000

Data Index: 170014 (The Pile)

Max Activating Token Index: 9