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

Dataset: The Pile

Neuron 5100 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0153. Min Act: -0.0000

Data Index: 1045696 (The Pile)

Max Activating Token Index: 3

Text #1

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0124. Min Act: -0.0000

Data Index: 615013 (The Pile)

Max Activating Token Index: 5

Text #2

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0089. Min Act: -0.0000

Data Index: 841449 (The Pile)

Max Activating Token Index: 3

Text #3

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0088. Min Act: -0.0000

Data Index: 644534 (The Pile)

Max Activating Token Index: 3

Text #4

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0085. Min Act: -0.0000

Data Index: 1875611 (The Pile)

Max Activating Token Index: 5

Text #5

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0085. Min Act: -0.0000

Data Index: 1713388 (The Pile)

Max Activating Token Index: 5

Text #6

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0081. Min Act: -0.0000

Data Index: 1313706 (The Pile)

Max Activating Token Index: 7

Text #7

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0077. Min Act: -0.0000

Data Index: 157439 (The Pile)

Max Activating Token Index: 78

Text #8

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0079. Min Act: -0.0000

Data Index: 1770231 (The Pile)

Max Activating Token Index: 3

Text #9

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0082. Min Act: -0.0000

Data Index: 405288 (The Pile)

Max Activating Token Index: 7

Text #10

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0078. Min Act: -0.0000

Data Index: 1241290 (The Pile)

Max Activating Token Index: 5

Text #11

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0076. Min Act: -0.0000

Data Index: 1428728 (The Pile)

Max Activating Token Index: 8

Text #12

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0074. Min Act: -0.0000

Data Index: 447195 (The Pile)

Max Activating Token Index: 5

Text #13

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0074. Min Act: -0.0000

Data Index: 1097866 (The Pile)

Max Activating Token Index: 8

Text #14

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0074. Min Act: -0.0000

Data Index: 1134323 (The Pile)

Max Activating Token Index: 7

Text #15

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0073. Min Act: -0.0000

Data Index: 489699 (The Pile)

Max Activating Token Index: 3

Text #16

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0073. Min Act: -0.0000

Data Index: 607411 (The Pile)

Max Activating Token Index: 3

Text #17

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0073. Min Act: -0.0000

Data Index: 1847937 (The Pile)

Max Activating Token Index: 3

Text #18

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0073. Min Act: -0.0000

Data Index: 98665 (The Pile)

Max Activating Token Index: 3

Text #19

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0073. Min Act: -0.0000

Data Index: 728474 (The Pile)

Max Activating Token Index: 5