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

Dataset: The Pile

Neuron 3385 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: 0.0840. Min Range: -0.0840

Max Act: 0.0840. Min Act: 0.0000

Data Index: 363728 (The Pile)

Max Activating Token Index: 8

Text #1

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0786. Min Act: 0.0000

Data Index: 444710 (The Pile)

Max Activating Token Index: 8

Text #2

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0667. Min Act: 0.0000

Data Index: 1524702 (The Pile)

Max Activating Token Index: 4

Text #3

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0670. Min Act: -0.0000

Data Index: 1515454 (The Pile)

Max Activating Token Index: 3

Text #4

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0631. Min Act: 0.0000

Data Index: 915461 (The Pile)

Max Activating Token Index: 2

Text #5

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0625. Min Act: 0.0000

Data Index: 1811476 (The Pile)

Max Activating Token Index: 5

Text #6

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0620. Min Act: 0.0000

Data Index: 1611790 (The Pile)

Max Activating Token Index: 8

Text #7

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0616. Min Act: 0.0000

Data Index: 486401 (The Pile)

Max Activating Token Index: 2

Text #8

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0597. Min Act: 0.0000

Data Index: 936891 (The Pile)

Max Activating Token Index: 8

Text #9

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0590. Min Act: -0.0000

Data Index: 1193537 (The Pile)

Max Activating Token Index: 13

Text #10

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0582. Min Act: 0.0000

Data Index: 1611332 (The Pile)

Max Activating Token Index: 18

Text #11

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0581. Min Act: -0.0000

Data Index: 1785501 (The Pile)

Max Activating Token Index: 13

Text #12

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0576. Min Act: 0.0000

Data Index: 1923592 (The Pile)

Max Activating Token Index: 3

Text #13

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0574. Min Act: 0.0000

Data Index: 1493596 (The Pile)

Max Activating Token Index: 9

Text #14

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0574. Min Act: 0.0000

Data Index: 691920 (The Pile)

Max Activating Token Index: 3

Text #15

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0572. Min Act: 0.0000

Data Index: 1793244 (The Pile)

Max Activating Token Index: 10

Text #16

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0589. Min Act: 0.0000

Data Index: 219602 (The Pile)

Max Activating Token Index: 11

Text #17

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0567. Min Act: 0.0000

Data Index: 1062732 (The Pile)

Max Activating Token Index: 11

Text #18

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0588. Min Act: 0.0000

Data Index: 528128 (The Pile)

Max Activating Token Index: 8

Text #19

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0559. Min Act: 0.0000

Data Index: 774336 (The Pile)

Max Activating Token Index: 5