Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1987 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1686. Min Act: -0.0000

Data Index: 1397958 (The Pile)

Max Activating Token Index: 812

Text #1

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1158. Min Act: -0.0000

Data Index: 998141 (The Pile)

Max Activating Token Index: 35

Text #2

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1157. Min Act: -0.0000

Data Index: 811966 (The Pile)

Max Activating Token Index: 709

Text #3

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1044. Min Act: -0.0000

Data Index: 1103701 (The Pile)

Max Activating Token Index: 431

Text #4

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1063. Min Act: -0.0000

Data Index: 1816304 (The Pile)

Max Activating Token Index: 391

Text #5

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1073. Min Act: -0.0000

Data Index: 1804112 (The Pile)

Max Activating Token Index: 49

Text #6

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1070. Min Act: -0.0000

Data Index: 1090932 (The Pile)

Max Activating Token Index: 719

Text #7

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1092. Min Act: -0.0000

Data Index: 211223 (The Pile)

Max Activating Token Index: 983

Text #8

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1070. Min Act: -0.0000

Data Index: 1290976 (The Pile)

Max Activating Token Index: 221

Text #9

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1112. Min Act: -0.0000

Data Index: 1102783 (The Pile)

Max Activating Token Index: 573

Text #10

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1109. Min Act: -0.0000

Data Index: 1035644 (The Pile)

Max Activating Token Index: 104

Text #11

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1031. Min Act: -0.0000

Data Index: 1233128 (The Pile)

Max Activating Token Index: 863

Text #12

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1067. Min Act: -0.0000

Data Index: 1830802 (The Pile)

Max Activating Token Index: 370

Text #13

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.0990. Min Act: -0.0000

Data Index: 1600832 (The Pile)

Max Activating Token Index: 93

Text #14

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1113. Min Act: -0.0000

Data Index: 716529 (The Pile)

Max Activating Token Index: 919

Text #15

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.0960. Min Act: -0.0000

Data Index: 710995 (The Pile)

Max Activating Token Index: 88

Text #16

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1058. Min Act: -0.0000

Data Index: 1185678 (The Pile)

Max Activating Token Index: 268

Text #17

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.0990. Min Act: -0.0000

Data Index: 569462 (The Pile)

Max Activating Token Index: 975

Text #18

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1057. Min Act: -0.0000

Data Index: 1569246 (The Pile)

Max Activating Token Index: 828

Text #19

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1045. Min Act: -0.0000

Data Index: 1452154 (The Pile)

Max Activating Token Index: 311