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

Dataset: The Pile

Neuron 4957 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: 1.0723. Min Range: -1.0723

Max Act: 0.9982. Min Act: -0.0000

Data Index: 1272361 (The Pile)

Max Activating Token Index: 554

Text #1

Max Range: 1.0723. Min Range: -1.0723

Max Act: 1.0069. Min Act: -0.0000

Data Index: 1528675 (The Pile)

Max Activating Token Index: 510

Text #2

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.7341. Min Act: -0.0000

Data Index: 378097 (The Pile)

Max Activating Token Index: 836

Text #3

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.8994. Min Act: -0.0000

Data Index: 1100475 (The Pile)

Max Activating Token Index: 441

Text #4

Max Range: 1.0723. Min Range: -1.0723

Max Act: 1.0723. Min Act: -0.0000

Data Index: 439976 (The Pile)

Max Activating Token Index: 850

Text #5

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.7239. Min Act: -0.0000

Data Index: 222943 (The Pile)

Max Activating Token Index: 737

Text #6

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.7987. Min Act: -0.0000

Data Index: 1452844 (The Pile)

Max Activating Token Index: 595

Text #7

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.8930. Min Act: -0.0000

Data Index: 323960 (The Pile)

Max Activating Token Index: 582

Text #8

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.7435. Min Act: -0.0000

Data Index: 647995 (The Pile)

Max Activating Token Index: 406

Text #9

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.7332. Min Act: -0.0000

Data Index: 421173 (The Pile)

Max Activating Token Index: 702

Text #10

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.6907. Min Act: -0.0000

Data Index: 448184 (The Pile)

Max Activating Token Index: 849

Text #11

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.6935. Min Act: -0.0000

Data Index: 384069 (The Pile)

Max Activating Token Index: 664

Text #12

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.5963. Min Act: -0.0000

Data Index: 1734723 (The Pile)

Max Activating Token Index: 610

Text #13

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.6975. Min Act: -0.0000

Data Index: 851978 (The Pile)

Max Activating Token Index: 245

Text #14

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.7752. Min Act: -0.0000

Data Index: 141778 (The Pile)

Max Activating Token Index: 484

Text #15

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.7810. Min Act: -0.0000

Data Index: 1858324 (The Pile)

Max Activating Token Index: 444

Text #16

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.7909. Min Act: -0.0000

Data Index: 1664487 (The Pile)

Max Activating Token Index: 914

Text #17

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.6638. Min Act: -0.0000

Data Index: 601651 (The Pile)

Max Activating Token Index: 204

Text #18

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.8273. Min Act: -0.0000

Data Index: 349432 (The Pile)

Max Activating Token Index: 635

Text #19

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.6946. Min Act: -0.0000

Data Index: 135105 (The Pile)

Max Activating Token Index: 602