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

Dataset: The Pile

Neuron 3911 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: 0.0599. Min Range: -0.0599

Max Act: 0.0599. Min Act: -0.0000

Data Index: 349514 (The Pile)

Max Activating Token Index: 1

Text #1

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0599. Min Act: -0.0000

Data Index: 1445422 (The Pile)

Max Activating Token Index: 1

Text #2

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0599. Min Act: -0.0000

Data Index: 1439471 (The Pile)

Max Activating Token Index: 1

Text #3

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0599. Min Act: -0.0000

Data Index: 995522 (The Pile)

Max Activating Token Index: 1

Text #4

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0544. Min Act: -0.0000

Data Index: 78598 (The Pile)

Max Activating Token Index: 1

Text #5

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0544. Min Act: -0.0000

Data Index: 913178 (The Pile)

Max Activating Token Index: 1

Text #6

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0544. Min Act: -0.0000

Data Index: 259132 (The Pile)

Max Activating Token Index: 1

Text #7

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0544. Min Act: -0.0000

Data Index: 1265012 (The Pile)

Max Activating Token Index: 1

Text #8

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0544. Min Act: -0.0000

Data Index: 1358761 (The Pile)

Max Activating Token Index: 1

Text #9

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0522. Min Act: -0.0000

Data Index: 1026722 (The Pile)

Max Activating Token Index: 1

Text #10

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0522. Min Act: -0.0000

Data Index: 1524335 (The Pile)

Max Activating Token Index: 1

Text #11

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0522. Min Act: -0.0000

Data Index: 1450736 (The Pile)

Max Activating Token Index: 1

Text #12

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0522. Min Act: -0.0000

Data Index: 1410931 (The Pile)

Max Activating Token Index: 1

Text #13

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0522. Min Act: -0.0000

Data Index: 743247 (The Pile)

Max Activating Token Index: 1

Text #14

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0522. Min Act: -0.0000

Data Index: 681496 (The Pile)

Max Activating Token Index: 1

Text #15

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0522. Min Act: -0.0000

Data Index: 435034 (The Pile)

Max Activating Token Index: 1

Text #16

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0522. Min Act: -0.0000

Data Index: 324123 (The Pile)

Max Activating Token Index: 1

Text #17

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0481. Min Act: -0.0000

Data Index: 145880 (The Pile)

Max Activating Token Index: 1

Text #18

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0481. Min Act: -0.0000

Data Index: 163036 (The Pile)

Max Activating Token Index: 1

Text #19

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0481. Min Act: -0.0000

Data Index: 611009 (The Pile)

Max Activating Token Index: 1