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

Dataset: The Pile

Neuron 2820 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0792. Min Act: -0.0000

Data Index: 427716 (The Pile)

Max Activating Token Index: 1020

Text #1

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0735. Min Act: -0.0000

Data Index: 1188552 (The Pile)

Max Activating Token Index: 641

Text #2

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0725. Min Act: -0.0000

Data Index: 1744594 (The Pile)

Max Activating Token Index: 435

Text #3

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0730. Min Act: -0.0000

Data Index: 920073 (The Pile)

Max Activating Token Index: 515

Text #4

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0734. Min Act: -0.0000

Data Index: 1790252 (The Pile)

Max Activating Token Index: 951

Text #5

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0714. Min Act: -0.0000

Data Index: 1392388 (The Pile)

Max Activating Token Index: 519

Text #6

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0681. Min Act: -0.0000

Data Index: 99945 (The Pile)

Max Activating Token Index: 441

Text #7

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0588. Min Act: -0.0000

Data Index: 332796 (The Pile)

Max Activating Token Index: 229

Text #8

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0587. Min Act: -0.0000

Data Index: 1179731 (The Pile)

Max Activating Token Index: 735

Text #9

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0578. Min Act: -0.0000

Data Index: 1577370 (The Pile)

Max Activating Token Index: 729

Text #10

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0583. Min Act: -0.0000

Data Index: 3881 (The Pile)

Max Activating Token Index: 352

Text #11

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0589. Min Act: -0.0000

Data Index: 884778 (The Pile)

Max Activating Token Index: 431

Text #12

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0627. Min Act: -0.0000

Data Index: 897755 (The Pile)

Max Activating Token Index: 18

Text #13

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0573. Min Act: -0.0000

Data Index: 1960641 (The Pile)

Max Activating Token Index: 503

Text #14

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0577. Min Act: -0.0000

Data Index: 571997 (The Pile)

Max Activating Token Index: 601

Text #15

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0522. Min Act: -0.0000

Data Index: 1567457 (The Pile)

Max Activating Token Index: 440

Text #16

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0559. Min Act: -0.0000

Data Index: 691215 (The Pile)

Max Activating Token Index: 546

Text #17

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0432. Min Act: -0.0000

Data Index: 1030321 (The Pile)

Max Activating Token Index: 842

Text #18

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0752. Min Act: -0.0000

Data Index: 556480 (The Pile)

Max Activating Token Index: 831

Text #19

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0603. Min Act: -0.0000

Data Index: 435930 (The Pile)

Max Activating Token Index: 173