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

Dataset: The Pile

Neuron 1041 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.5412. Min Act: -0.0000

Data Index: 318903 (The Pile)

Max Activating Token Index: 455

Text #1

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.5339. Min Act: -0.0000

Data Index: 1173169 (The Pile)

Max Activating Token Index: 619

Text #2

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.5555. Min Act: -0.0000

Data Index: 511324 (The Pile)

Max Activating Token Index: 755

Text #3

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.4382. Min Act: -0.0000

Data Index: 1052574 (The Pile)

Max Activating Token Index: 86

Text #4

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.3871. Min Act: -0.0000

Data Index: 1967794 (The Pile)

Max Activating Token Index: 648

Text #5

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.4000. Min Act: -0.0000

Data Index: 1979003 (The Pile)

Max Activating Token Index: 399

Text #6

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.4077. Min Act: -0.0000

Data Index: 1206237 (The Pile)

Max Activating Token Index: 656

Text #7

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.4102. Min Act: -0.0000

Data Index: 1374712 (The Pile)

Max Activating Token Index: 926

Text #8

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.3681. Min Act: -0.0000

Data Index: 1007833 (The Pile)

Max Activating Token Index: 854

Text #9

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.4121. Min Act: -0.0000

Data Index: 404166 (The Pile)

Max Activating Token Index: 149

Text #10

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.3882. Min Act: -0.0000

Data Index: 855897 (The Pile)

Max Activating Token Index: 194

Text #11

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.3614. Min Act: -0.0000

Data Index: 428756 (The Pile)

Max Activating Token Index: 1011

Text #12

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.3748. Min Act: -0.0000

Data Index: 1916131 (The Pile)

Max Activating Token Index: 851

Text #13

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.4169. Min Act: 0.0001

Data Index: 481964 (The Pile)

Max Activating Token Index: 280

Text #14

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.4020. Min Act: 0.0000

Data Index: 1397771 (The Pile)

Max Activating Token Index: 115

Text #15

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.3635. Min Act: -0.0000

Data Index: 1568128 (The Pile)

Max Activating Token Index: 220

Text #16

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.4056. Min Act: -0.0000

Data Index: 152769 (The Pile)

Max Activating Token Index: 906

Text #17

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.3591. Min Act: 0.0000

Data Index: 501781 (The Pile)

Max Activating Token Index: 892

Text #18

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.3712. Min Act: 0.0000

Data Index: 171562 (The Pile)

Max Activating Token Index: 563

Text #19

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.3840. Min Act: 0.0000

Data Index: 537654 (The Pile)

Max Activating Token Index: 363