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

Dataset: The Pile

Neuron 3683 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: 0.4778. Min Range: -0.4778

Max Act: 0.4778. Min Act: -0.0000

Data Index: 656731 (The Pile)

Max Activating Token Index: 587

Text #1

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.4227. Min Act: -0.0000

Data Index: 1888302 (The Pile)

Max Activating Token Index: 537

Text #2

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.4362. Min Act: -0.0000

Data Index: 1580404 (The Pile)

Max Activating Token Index: 685

Text #3

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.4252. Min Act: -0.0000

Data Index: 423862 (The Pile)

Max Activating Token Index: 665

Text #4

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.4515. Min Act: -0.0000

Data Index: 1038424 (The Pile)

Max Activating Token Index: 937

Text #5

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.4627. Min Act: -0.0000

Data Index: 449311 (The Pile)

Max Activating Token Index: 661

Text #6

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.3827. Min Act: -0.0000

Data Index: 934827 (The Pile)

Max Activating Token Index: 110

Text #7

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.4076. Min Act: -0.0000

Data Index: 329847 (The Pile)

Max Activating Token Index: 531

Text #8

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.3656. Min Act: -0.0000

Data Index: 697085 (The Pile)

Max Activating Token Index: 910

Text #9

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.4536. Min Act: -0.0000

Data Index: 949886 (The Pile)

Max Activating Token Index: 974

Text #10

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.4014. Min Act: -0.0000

Data Index: 656979 (The Pile)

Max Activating Token Index: 629

Text #11

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.3750. Min Act: -0.0000

Data Index: 1357959 (The Pile)

Max Activating Token Index: 356

Text #12

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.4283. Min Act: -0.0000

Data Index: 548842 (The Pile)

Max Activating Token Index: 730

Text #13

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.4013. Min Act: -0.0000

Data Index: 570044 (The Pile)

Max Activating Token Index: 552

Text #14

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.3948. Min Act: -0.0000

Data Index: 472493 (The Pile)

Max Activating Token Index: 511

Text #15

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.3792. Min Act: -0.0000

Data Index: 1308669 (The Pile)

Max Activating Token Index: 424

Text #16

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.3893. Min Act: -0.0000

Data Index: 1293554 (The Pile)

Max Activating Token Index: 626

Text #17

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.3800. Min Act: -0.0000

Data Index: 483372 (The Pile)

Max Activating Token Index: 318

Text #18

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.3631. Min Act: -0.0000

Data Index: 289843 (The Pile)

Max Activating Token Index: 424

Text #19

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.3416. Min Act: -0.0000

Data Index: 1567356 (The Pile)

Max Activating Token Index: 604