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

Dataset: The Pile

Neuron 3993 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1696. Min Act: -0.0000

Data Index: 791705 (The Pile)

Max Activating Token Index: 408

Text #1

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1082. Min Act: -0.0000

Data Index: 1605365 (The Pile)

Max Activating Token Index: 971

Text #2

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1079. Min Act: -0.0000

Data Index: 518972 (The Pile)

Max Activating Token Index: 996

Text #3

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1259. Min Act: -0.0000

Data Index: 639392 (The Pile)

Max Activating Token Index: 30

Text #4

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1268. Min Act: -0.0000

Data Index: 1501277 (The Pile)

Max Activating Token Index: 102

Text #5

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1147. Min Act: -0.0000

Data Index: 43137 (The Pile)

Max Activating Token Index: 22

Text #6

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1285. Min Act: -0.0000

Data Index: 1212853 (The Pile)

Max Activating Token Index: 812

Text #7

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1063. Min Act: -0.0000

Data Index: 1325551 (The Pile)

Max Activating Token Index: 652

Text #8

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1221. Min Act: -0.0000

Data Index: 371040 (The Pile)

Max Activating Token Index: 692

Text #9

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1046. Min Act: -0.0000

Data Index: 733898 (The Pile)

Max Activating Token Index: 64

Text #10

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1114. Min Act: -0.0000

Data Index: 623595 (The Pile)

Max Activating Token Index: 987

Text #11

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1069. Min Act: -0.0000

Data Index: 1134202 (The Pile)

Max Activating Token Index: 160

Text #12

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.0940. Min Act: -0.0000

Data Index: 1051689 (The Pile)

Max Activating Token Index: 1001

Text #13

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.0841. Min Act: -0.0000

Data Index: 204147 (The Pile)

Max Activating Token Index: 585

Text #14

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1089. Min Act: -0.0000

Data Index: 1348376 (The Pile)

Max Activating Token Index: 769

Text #15

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1045. Min Act: -0.0000

Data Index: 332748 (The Pile)

Max Activating Token Index: 95

Text #16

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.0985. Min Act: -0.0000

Data Index: 1317729 (The Pile)

Max Activating Token Index: 65

Text #17

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1009. Min Act: -0.0000

Data Index: 1665568 (The Pile)

Max Activating Token Index: 38

Text #18

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.0991. Min Act: -0.0000

Data Index: 1455134 (The Pile)

Max Activating Token Index: 30

Text #19

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.0888. Min Act: -0.0000

Data Index: 1028415 (The Pile)

Max Activating Token Index: 37