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

Dataset: The Pile

Neuron 1041 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.1241. Min Act: -0.0000

Data Index: 557233 (The Pile)

Max Activating Token Index: 11

Text #1

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.1160. Min Act: -0.0000

Data Index: 616314 (The Pile)

Max Activating Token Index: 74

Text #2

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.1192. Min Act: -0.0000

Data Index: 470471 (The Pile)

Max Activating Token Index: 1012

Text #3

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.1074. Min Act: -0.0000

Data Index: 657120 (The Pile)

Max Activating Token Index: 784

Text #4

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0998. Min Act: -0.0000

Data Index: 69754 (The Pile)

Max Activating Token Index: 22

Text #5

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0987. Min Act: -0.0000

Data Index: 268268 (The Pile)

Max Activating Token Index: 828

Text #6

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.1060. Min Act: -0.0000

Data Index: 327860 (The Pile)

Max Activating Token Index: 936

Text #7

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.1072. Min Act: -0.0000

Data Index: 1880484 (The Pile)

Max Activating Token Index: 421

Text #8

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.1102. Min Act: -0.0000

Data Index: 361608 (The Pile)

Max Activating Token Index: 416

Text #9

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.1095. Min Act: -0.0000

Data Index: 81700 (The Pile)

Max Activating Token Index: 937

Text #10

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.1112. Min Act: -0.0000

Data Index: 1571765 (The Pile)

Max Activating Token Index: 15

Text #11

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0903. Min Act: -0.0000

Data Index: 272994 (The Pile)

Max Activating Token Index: 29

Text #12

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.1153. Min Act: -0.0000

Data Index: 250034 (The Pile)

Max Activating Token Index: 255

Text #13

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.1090. Min Act: -0.0000

Data Index: 1897353 (The Pile)

Max Activating Token Index: 694

Text #14

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0981. Min Act: -0.0000

Data Index: 346365 (The Pile)

Max Activating Token Index: 107

Text #15

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0842. Min Act: -0.0000

Data Index: 1447484 (The Pile)

Max Activating Token Index: 728

Text #16

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0951. Min Act: -0.0000

Data Index: 488215 (The Pile)

Max Activating Token Index: 691

Text #17

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0924. Min Act: -0.0000

Data Index: 672522 (The Pile)

Max Activating Token Index: 846

Text #18

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0823. Min Act: -0.0000

Data Index: 12447 (The Pile)

Max Activating Token Index: 905

Text #19

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0906. Min Act: -0.0000

Data Index: 1371683 (The Pile)

Max Activating Token Index: 768