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

Dataset: The Pile

Neuron 2569 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: 0.8932. Min Range: -0.8932

Max Act: 0.8875. Min Act: -0.0000

Data Index: 1429195 (The Pile)

Max Activating Token Index: 480

Text #1

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.8932. Min Act: -0.0000

Data Index: 786141 (The Pile)

Max Activating Token Index: 584

Text #2

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.8659. Min Act: -0.0000

Data Index: 1202464 (The Pile)

Max Activating Token Index: 324

Text #3

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.8305. Min Act: -0.0000

Data Index: 966877 (The Pile)

Max Activating Token Index: 389

Text #4

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.7847. Min Act: -0.0000

Data Index: 1121242 (The Pile)

Max Activating Token Index: 592

Text #5

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.8631. Min Act: -0.0000

Data Index: 1624901 (The Pile)

Max Activating Token Index: 725

Text #6

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.7615. Min Act: -0.0000

Data Index: 627517 (The Pile)

Max Activating Token Index: 631

Text #7

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.7978. Min Act: -0.0000

Data Index: 1559206 (The Pile)

Max Activating Token Index: 89

Text #8

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.8282. Min Act: -0.0000

Data Index: 638541 (The Pile)

Max Activating Token Index: 886

Text #9

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.7634. Min Act: -0.0000

Data Index: 1494303 (The Pile)

Max Activating Token Index: 318

Text #10

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.7999. Min Act: -0.0000

Data Index: 1333592 (The Pile)

Max Activating Token Index: 543

Text #11

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.7375. Min Act: -0.0000

Data Index: 1597794 (The Pile)

Max Activating Token Index: 675

Text #12

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.7285. Min Act: -0.0000

Data Index: 1029745 (The Pile)

Max Activating Token Index: 765

Text #13

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.6898. Min Act: -0.0000

Data Index: 720049 (The Pile)

Max Activating Token Index: 137

Text #14

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.5760. Min Act: -0.0000

Data Index: 1303670 (The Pile)

Max Activating Token Index: 819

Text #15

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.7175. Min Act: -0.0000

Data Index: 1893064 (The Pile)

Max Activating Token Index: 573

Text #16

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.6720. Min Act: -0.0000

Data Index: 1178419 (The Pile)

Max Activating Token Index: 471

Text #17

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.7088. Min Act: -0.0000

Data Index: 1293647 (The Pile)

Max Activating Token Index: 927

Text #18

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.7882. Min Act: -0.0000

Data Index: 777455 (The Pile)

Max Activating Token Index: 983

Text #19

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.7630. Min Act: -0.0000

Data Index: 1077054 (The Pile)

Max Activating Token Index: 863