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

Dataset: The Pile

Neuron 1474 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.8865. Min Act: -0.0000

Data Index: 1969305 (The Pile)

Max Activating Token Index: 469

Text #1

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.8769. Min Act: -0.0000

Data Index: 454473 (The Pile)

Max Activating Token Index: 826

Text #2

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.9402. Min Act: -0.0000

Data Index: 1598862 (The Pile)

Max Activating Token Index: 449

Text #3

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7715. Min Act: -0.0000

Data Index: 766044 (The Pile)

Max Activating Token Index: 675

Text #4

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7720. Min Act: -0.0000

Data Index: 469731 (The Pile)

Max Activating Token Index: 544

Text #5

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7712. Min Act: -0.0000

Data Index: 1014409 (The Pile)

Max Activating Token Index: 403

Text #6

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7756. Min Act: -0.0000

Data Index: 343276 (The Pile)

Max Activating Token Index: 890

Text #7

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.8377. Min Act: -0.0000

Data Index: 138964 (The Pile)

Max Activating Token Index: 950

Text #8

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7940. Min Act: -0.0000

Data Index: 878089 (The Pile)

Max Activating Token Index: 658

Text #9

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7737. Min Act: -0.0000

Data Index: 1065808 (The Pile)

Max Activating Token Index: 115

Text #10

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7771. Min Act: -0.0000

Data Index: 1527116 (The Pile)

Max Activating Token Index: 961

Text #11

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.8040. Min Act: -0.0000

Data Index: 197216 (The Pile)

Max Activating Token Index: 864

Text #12

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7725. Min Act: -0.0000

Data Index: 364746 (The Pile)

Max Activating Token Index: 870

Text #13

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7731. Min Act: -0.0000

Data Index: 384512 (The Pile)

Max Activating Token Index: 755

Text #14

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7086. Min Act: -0.0000

Data Index: 1614573 (The Pile)

Max Activating Token Index: 968

Text #15

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7703. Min Act: -0.0000

Data Index: 147057 (The Pile)

Max Activating Token Index: 753

Text #16

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7713. Min Act: -0.0000

Data Index: 1890102 (The Pile)

Max Activating Token Index: 470

Text #17

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7136. Min Act: -0.0000

Data Index: 1912362 (The Pile)

Max Activating Token Index: 984

Text #18

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.6501. Min Act: -0.0000

Data Index: 1592216 (The Pile)

Max Activating Token Index: 941

Text #19

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7196. Min Act: -0.0000

Data Index: 230880 (The Pile)

Max Activating Token Index: 462