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

Dataset: The Pile

Neuron 582 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0156. Min Act: -0.0000

Data Index: 1485007 (The Pile)

Max Activating Token Index: 1

Text #1

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0156. Min Act: -0.0000

Data Index: 888048 (The Pile)

Max Activating Token Index: 1

Text #2

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0156. Min Act: -0.0000

Data Index: 1717098 (The Pile)

Max Activating Token Index: 1

Text #3

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0156. Min Act: 0.0000

Data Index: 1570094 (The Pile)

Max Activating Token Index: 1

Text #4

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0156. Min Act: -0.0000

Data Index: 838454 (The Pile)

Max Activating Token Index: 1

Text #5

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0156. Min Act: 0.0000

Data Index: 579388 (The Pile)

Max Activating Token Index: 1

Text #6

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0156. Min Act: 0.0000

Data Index: 1637976 (The Pile)

Max Activating Token Index: 1

Text #7

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0156. Min Act: 0.0000

Data Index: 636722 (The Pile)

Max Activating Token Index: 1

Text #8

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0156. Min Act: -0.0000

Data Index: 1406397 (The Pile)

Max Activating Token Index: 1

Text #9

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0156. Min Act: -0.0000

Data Index: 1919685 (The Pile)

Max Activating Token Index: 1

Text #10

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0156. Min Act: -0.0000

Data Index: 1730555 (The Pile)

Max Activating Token Index: 1

Text #11

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0156. Min Act: -0.0000

Data Index: 231249 (The Pile)

Max Activating Token Index: 1

Text #12

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0134. Min Act: 0.0000

Data Index: 1810367 (The Pile)

Max Activating Token Index: 3

Text #13

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0134. Min Act: -0.0000

Data Index: 1708272 (The Pile)

Max Activating Token Index: 4

Text #14

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0138. Min Act: -0.0000

Data Index: 1879170 (The Pile)

Max Activating Token Index: 9

Text #15

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0130. Min Act: -0.0000

Data Index: 1061768 (The Pile)

Max Activating Token Index: 2

Text #16

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0130. Min Act: -0.0000

Data Index: 1950734 (The Pile)

Max Activating Token Index: 3

Text #17

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0129. Min Act: -0.0000

Data Index: 1371013 (The Pile)

Max Activating Token Index: 3

Text #18

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0129. Min Act: -0.0000

Data Index: 416798 (The Pile)

Max Activating Token Index: 3

Text #19

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0128. Min Act: -0.0000

Data Index: 732070 (The Pile)

Max Activating Token Index: 30