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

Dataset: The Pile

Neuron 2813 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: 0.0519. Min Range: -0.0519

Max Act: 0.0519. Min Act: 0.0000

Data Index: 1932349 (The Pile)

Max Activating Token Index: 1

Text #1

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0519. Min Act: 0.0000

Data Index: 1671426 (The Pile)

Max Activating Token Index: 1

Text #2

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0519. Min Act: 0.0000

Data Index: 778169 (The Pile)

Max Activating Token Index: 1

Text #3

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0519. Min Act: 0.0000

Data Index: 818960 (The Pile)

Max Activating Token Index: 1

Text #4

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0502. Min Act: 0.0000

Data Index: 1450484 (The Pile)

Max Activating Token Index: 1

Text #5

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0502. Min Act: 0.0000

Data Index: 1433792 (The Pile)

Max Activating Token Index: 1

Text #6

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0502. Min Act: -0.0000

Data Index: 1413788 (The Pile)

Max Activating Token Index: 1

Text #7

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0502. Min Act: -0.0000

Data Index: 442094 (The Pile)

Max Activating Token Index: 1

Text #8

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0502. Min Act: -0.0000

Data Index: 1259279 (The Pile)

Max Activating Token Index: 1

Text #9

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0502. Min Act: -0.0000

Data Index: 1067576 (The Pile)

Max Activating Token Index: 1

Text #10

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0502. Min Act: -0.0000

Data Index: 346841 (The Pile)

Max Activating Token Index: 1

Text #11

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0502. Min Act: -0.0000

Data Index: 969511 (The Pile)

Max Activating Token Index: 1

Text #12

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0502. Min Act: -0.0000

Data Index: 386309 (The Pile)

Max Activating Token Index: 1

Text #13

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0502. Min Act: 0.0000

Data Index: 845095 (The Pile)

Max Activating Token Index: 1

Text #14

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0502. Min Act: 0.0000

Data Index: 840727 (The Pile)

Max Activating Token Index: 1

Text #15

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0502. Min Act: 0.0000

Data Index: 349888 (The Pile)

Max Activating Token Index: 1

Text #16

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0502. Min Act: -0.0000

Data Index: 148750 (The Pile)

Max Activating Token Index: 1

Text #17

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0502. Min Act: -0.0000

Data Index: 786812 (The Pile)

Max Activating Token Index: 1

Text #18

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0502. Min Act: 0.0000

Data Index: 666358 (The Pile)

Max Activating Token Index: 1

Text #19

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0502. Min Act: -0.0000

Data Index: 557020 (The Pile)

Max Activating Token Index: 1