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

Dataset: The Pile

Neuron 3321 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: 1.0203. Min Range: -1.0203

Max Act: 1.0203. Min Act: -0.0000

Data Index: 1844598 (The Pile)

Max Activating Token Index: 331

Text #1

Max Range: 1.0203. Min Range: -1.0203

Max Act: 0.9515. Min Act: -0.0000

Data Index: 665609 (The Pile)

Max Activating Token Index: 961

Text #2

Max Range: 1.0203. Min Range: -1.0203

Max Act: 1.0125. Min Act: -0.0000

Data Index: 1970835 (The Pile)

Max Activating Token Index: 744

Text #3

Max Range: 1.0203. Min Range: -1.0203

Max Act: 0.8740. Min Act: -0.0000

Data Index: 396537 (The Pile)

Max Activating Token Index: 484

Text #4

Max Range: 1.0203. Min Range: -1.0203

Max Act: 0.8681. Min Act: -0.0000

Data Index: 236627 (The Pile)

Max Activating Token Index: 717

Text #5

Max Range: 1.0203. Min Range: -1.0203

Max Act: 0.9181. Min Act: -0.0000

Data Index: 411777 (The Pile)

Max Activating Token Index: 881

Text #6

Max Range: 1.0203. Min Range: -1.0203

Max Act: 0.8690. Min Act: -0.0000

Data Index: 633846 (The Pile)

Max Activating Token Index: 587

Text #7

Max Range: 1.0203. Min Range: -1.0203

Max Act: 0.8979. Min Act: -0.0000

Data Index: 795310 (The Pile)

Max Activating Token Index: 452

Text #8

Max Range: 1.0203. Min Range: -1.0203

Max Act: 0.7996. Min Act: -0.0000

Data Index: 39060 (The Pile)

Max Activating Token Index: 904

Text #9

Max Range: 1.0203. Min Range: -1.0203

Max Act: 0.8040. Min Act: -0.0000

Data Index: 1733810 (The Pile)

Max Activating Token Index: 297

Text #10

Max Range: 1.0203. Min Range: -1.0203

Max Act: 0.7472. Min Act: -0.0000

Data Index: 1816750 (The Pile)

Max Activating Token Index: 799

Text #11

Max Range: 1.0203. Min Range: -1.0203

Max Act: 0.7859. Min Act: -0.0000

Data Index: 959168 (The Pile)

Max Activating Token Index: 664

Text #12

Max Range: 1.0203. Min Range: -1.0203

Max Act: 0.7888. Min Act: -0.0000

Data Index: 1397880 (The Pile)

Max Activating Token Index: 50

Text #13

Max Range: 1.0203. Min Range: -1.0203

Max Act: 0.8211. Min Act: -0.0000

Data Index: 1129209 (The Pile)

Max Activating Token Index: 34

Text #14

Max Range: 1.0203. Min Range: -1.0203

Max Act: 0.7844. Min Act: -0.0000

Data Index: 1507267 (The Pile)

Max Activating Token Index: 774

Text #15

Max Range: 1.0203. Min Range: -1.0203

Max Act: 0.7647. Min Act: -0.0000

Data Index: 233265 (The Pile)

Max Activating Token Index: 335

Text #16

Max Range: 1.0203. Min Range: -1.0203

Max Act: 0.7685. Min Act: -0.0000

Data Index: 28604 (The Pile)

Max Activating Token Index: 569

Text #17

Max Range: 1.0203. Min Range: -1.0203

Max Act: 0.7464. Min Act: -0.0000

Data Index: 1807009 (The Pile)

Max Activating Token Index: 923

Text #18

Max Range: 1.0203. Min Range: -1.0203

Max Act: 0.7855. Min Act: -0.0000

Data Index: 1148519 (The Pile)

Max Activating Token Index: 518

Text #19

Max Range: 1.0203. Min Range: -1.0203

Max Act: 0.6948. Min Act: -0.0000

Data Index: 470559 (The Pile)

Max Activating Token Index: 83