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

Dataset: The Pile

Neuron 2975 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: 0.1667. Min Range: -0.1667

Max Act: 0.1667. Min Act: -0.0000

Data Index: 1781659 (The Pile)

Max Activating Token Index: 157

Text #1

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1341. Min Act: -0.0000

Data Index: 1759857 (The Pile)

Max Activating Token Index: 224

Text #2

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1490. Min Act: -0.0000

Data Index: 1461481 (The Pile)

Max Activating Token Index: 897

Text #3

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1300. Min Act: -0.0000

Data Index: 175194 (The Pile)

Max Activating Token Index: 80

Text #4

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1418. Min Act: -0.0000

Data Index: 1466531 (The Pile)

Max Activating Token Index: 469

Text #5

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1365. Min Act: -0.0000

Data Index: 1590129 (The Pile)

Max Activating Token Index: 278

Text #6

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1239. Min Act: -0.0000

Data Index: 120177 (The Pile)

Max Activating Token Index: 171

Text #7

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1132. Min Act: -0.0000

Data Index: 96656 (The Pile)

Max Activating Token Index: 47

Text #8

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1173. Min Act: -0.0000

Data Index: 746091 (The Pile)

Max Activating Token Index: 477

Text #9

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1179. Min Act: -0.0000

Data Index: 1632280 (The Pile)

Max Activating Token Index: 59

Text #10

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1147. Min Act: -0.0000

Data Index: 1293753 (The Pile)

Max Activating Token Index: 118

Text #11

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.0986. Min Act: -0.0000

Data Index: 1034474 (The Pile)

Max Activating Token Index: 997

Text #12

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1095. Min Act: -0.0000

Data Index: 1630937 (The Pile)

Max Activating Token Index: 185

Text #13

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1000. Min Act: -0.0000

Data Index: 993906 (The Pile)

Max Activating Token Index: 148

Text #14

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.0997. Min Act: -0.0000

Data Index: 634126 (The Pile)

Max Activating Token Index: 524

Text #15

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1064. Min Act: -0.0000

Data Index: 416913 (The Pile)

Max Activating Token Index: 446

Text #16

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1064. Min Act: -0.0000

Data Index: 148216 (The Pile)

Max Activating Token Index: 16

Text #17

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1048. Min Act: -0.0000

Data Index: 36906 (The Pile)

Max Activating Token Index: 469

Text #18

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1040. Min Act: -0.0000

Data Index: 164907 (The Pile)

Max Activating Token Index: 159

Text #19

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1015. Min Act: -0.0000

Data Index: 1788141 (The Pile)

Max Activating Token Index: 301