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

Dataset: The Pile

Neuron 3202 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.9707. Min Act: -0.0000

Data Index: 1159850 (The Pile)

Max Activating Token Index: 111

Text #1

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.8959. Min Act: -0.0000

Data Index: 140485 (The Pile)

Max Activating Token Index: 472

Text #2

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.8380. Min Act: 0.0000

Data Index: 436163 (The Pile)

Max Activating Token Index: 1009

Text #3

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.8588. Min Act: -0.0000

Data Index: 1771214 (The Pile)

Max Activating Token Index: 724

Text #4

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.8689. Min Act: -0.0000

Data Index: 590499 (The Pile)

Max Activating Token Index: 1000

Text #5

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.8112. Min Act: 0.0000

Data Index: 1625648 (The Pile)

Max Activating Token Index: 949

Text #6

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.8623. Min Act: -0.0000

Data Index: 1770985 (The Pile)

Max Activating Token Index: 169

Text #7

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.8089. Min Act: 0.0000

Data Index: 1492906 (The Pile)

Max Activating Token Index: 36

Text #8

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.8235. Min Act: 0.0000

Data Index: 145686 (The Pile)

Max Activating Token Index: 408

Text #9

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.7834. Min Act: -0.0000

Data Index: 1840866 (The Pile)

Max Activating Token Index: 995

Text #10

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.7860. Min Act: -0.0000

Data Index: 1620298 (The Pile)

Max Activating Token Index: 118

Text #11

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.7833. Min Act: -0.0000

Data Index: 1521583 (The Pile)

Max Activating Token Index: 893

Text #12

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.7738. Min Act: 0.0000

Data Index: 1992768 (The Pile)

Max Activating Token Index: 680

Text #13

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.7145. Min Act: -0.0000

Data Index: 1635551 (The Pile)

Max Activating Token Index: 983

Text #14

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.7620. Min Act: -0.0000

Data Index: 1580457 (The Pile)

Max Activating Token Index: 83

Text #15

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.7543. Min Act: 0.0000

Data Index: 1714142 (The Pile)

Max Activating Token Index: 35

Text #16

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.7301. Min Act: -0.0000

Data Index: 1539523 (The Pile)

Max Activating Token Index: 349

Text #17

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.7321. Min Act: -0.0000

Data Index: 1453574 (The Pile)

Max Activating Token Index: 86

Text #18

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.7512. Min Act: -0.0000

Data Index: 406457 (The Pile)

Max Activating Token Index: 869

Text #19

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.7237. Min Act: -0.0000

Data Index: 1414467 (The Pile)

Max Activating Token Index: 54