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

Dataset: The Pile

Neuron 3780 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: 0.0869. Min Range: -0.0869

Max Act: 0.0869. Min Act: -0.0000

Data Index: 1849778 (The Pile)

Max Activating Token Index: 2

Text #1

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0836. Min Act: 0.0000

Data Index: 1129561 (The Pile)

Max Activating Token Index: 4

Text #2

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0794. Min Act: 0.0000

Data Index: 789699 (The Pile)

Max Activating Token Index: 3

Text #3

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0801. Min Act: 0.0000

Data Index: 404642 (The Pile)

Max Activating Token Index: 2

Text #4

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0801. Min Act: 0.0000

Data Index: 1646165 (The Pile)

Max Activating Token Index: 2

Text #5

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0760. Min Act: 0.0000

Data Index: 775440 (The Pile)

Max Activating Token Index: 6

Text #6

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0745. Min Act: 0.0000

Data Index: 399539 (The Pile)

Max Activating Token Index: 7

Text #7

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0744. Min Act: -0.0000

Data Index: 212395 (The Pile)

Max Activating Token Index: 2

Text #8

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0728. Min Act: 0.0000

Data Index: 866346 (The Pile)

Max Activating Token Index: 14

Text #9

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0723. Min Act: 0.0000

Data Index: 1380787 (The Pile)

Max Activating Token Index: 11

Text #10

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0723. Min Act: 0.0000

Data Index: 1787102 (The Pile)

Max Activating Token Index: 6

Text #11

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0722. Min Act: -0.0000

Data Index: 764734 (The Pile)

Max Activating Token Index: 3

Text #12

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0720. Min Act: 0.0000

Data Index: 935751 (The Pile)

Max Activating Token Index: 10

Text #13

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0716. Min Act: -0.0000

Data Index: 455373 (The Pile)

Max Activating Token Index: 4

Text #14

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0713. Min Act: -0.0000

Data Index: 1461218 (The Pile)

Max Activating Token Index: 24

Text #15

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0713. Min Act: 0.0000

Data Index: 1435047 (The Pile)

Max Activating Token Index: 3

Text #16

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0714. Min Act: 0.0000

Data Index: 437399 (The Pile)

Max Activating Token Index: 16

Text #17

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0711. Min Act: 0.0000

Data Index: 803668 (The Pile)

Max Activating Token Index: 6

Text #18

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0710. Min Act: 0.0000

Data Index: 1962283 (The Pile)

Max Activating Token Index: 6

Text #19

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0709. Min Act: 0.0000

Data Index: 875807 (The Pile)

Max Activating Token Index: 6