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

Dataset: The Pile

Neuron 511 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.1096. Min Act: -0.0000

Data Index: 1820189 (The Pile)

Max Activating Token Index: 993

Text #1

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.8010. Min Act: -0.0000

Data Index: 1070725 (The Pile)

Max Activating Token Index: 35

Text #2

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.8405. Min Act: -0.0000

Data Index: 1356549 (The Pile)

Max Activating Token Index: 903

Text #3

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.8921. Min Act: -0.0000

Data Index: 1564492 (The Pile)

Max Activating Token Index: 158

Text #4

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.7930. Min Act: -0.0000

Data Index: 1927714 (The Pile)

Max Activating Token Index: 508

Text #5

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.7531. Min Act: -0.0000

Data Index: 1819966 (The Pile)

Max Activating Token Index: 284

Text #6

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.7999. Min Act: -0.0000

Data Index: 600504 (The Pile)

Max Activating Token Index: 987

Text #7

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.7751. Min Act: -0.0000

Data Index: 686986 (The Pile)

Max Activating Token Index: 51

Text #8

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.7969. Min Act: -0.0000

Data Index: 517256 (The Pile)

Max Activating Token Index: 72

Text #9

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.7441. Min Act: -0.0000

Data Index: 1744409 (The Pile)

Max Activating Token Index: 25

Text #10

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.7536. Min Act: -0.0000

Data Index: 1057933 (The Pile)

Max Activating Token Index: 969

Text #11

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.7021. Min Act: -0.0000

Data Index: 433120 (The Pile)

Max Activating Token Index: 27

Text #12

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.6767. Min Act: -0.0000

Data Index: 442974 (The Pile)

Max Activating Token Index: 948

Text #13

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.7207. Min Act: -0.0000

Data Index: 1275496 (The Pile)

Max Activating Token Index: 391

Text #14

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.7151. Min Act: -0.0000

Data Index: 1593059 (The Pile)

Max Activating Token Index: 187

Text #15

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.7097. Min Act: -0.0000

Data Index: 450426 (The Pile)

Max Activating Token Index: 305

Text #16

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.7109. Min Act: -0.0000

Data Index: 1261942 (The Pile)

Max Activating Token Index: 334

Text #17

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.6686. Min Act: -0.0000

Data Index: 1558916 (The Pile)

Max Activating Token Index: 88

Text #18

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.6971. Min Act: -0.0000

Data Index: 500196 (The Pile)

Max Activating Token Index: 568

Text #19

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.7255. Min Act: -0.0000

Data Index: 1781072 (The Pile)

Max Activating Token Index: 321