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

Dataset: The Pile

Neuron 4505 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: 1.6807. Min Range: -1.6807

Max Act: 1.6807. Min Act: -0.0000

Data Index: 172440 (The Pile)

Max Activating Token Index: 83

Text #1

Max Range: 1.6807. Min Range: -1.6807

Max Act: 1.4055. Min Act: -0.0000

Data Index: 64988 (The Pile)

Max Activating Token Index: 567

Text #2

Max Range: 1.6807. Min Range: -1.6807

Max Act: 1.3386. Min Act: -0.0000

Data Index: 333595 (The Pile)

Max Activating Token Index: 398

Text #3

Max Range: 1.6807. Min Range: -1.6807

Max Act: 1.2380. Min Act: -0.0000

Data Index: 715851 (The Pile)

Max Activating Token Index: 918

Text #4

Max Range: 1.6807. Min Range: -1.6807

Max Act: 1.2033. Min Act: -0.0000

Data Index: 882241 (The Pile)

Max Activating Token Index: 722

Text #5

Max Range: 1.6807. Min Range: -1.6807

Max Act: 1.2780. Min Act: -0.0000

Data Index: 1420255 (The Pile)

Max Activating Token Index: 269

Text #6

Max Range: 1.6807. Min Range: -1.6807

Max Act: 1.2435. Min Act: -0.0000

Data Index: 895549 (The Pile)

Max Activating Token Index: 351

Text #7

Max Range: 1.6807. Min Range: -1.6807

Max Act: 1.2833. Min Act: -0.0000

Data Index: 531472 (The Pile)

Max Activating Token Index: 740

Text #8

Max Range: 1.6807. Min Range: -1.6807

Max Act: 1.1315. Min Act: -0.0000

Data Index: 380729 (The Pile)

Max Activating Token Index: 960

Text #9

Max Range: 1.6807. Min Range: -1.6807

Max Act: 1.1927. Min Act: -0.0000

Data Index: 812082 (The Pile)

Max Activating Token Index: 610

Text #10

Max Range: 1.6807. Min Range: -1.6807

Max Act: 1.0889. Min Act: -0.0000

Data Index: 1454696 (The Pile)

Max Activating Token Index: 751

Text #11

Max Range: 1.6807. Min Range: -1.6807

Max Act: 1.1531. Min Act: -0.0000

Data Index: 299432 (The Pile)

Max Activating Token Index: 23

Text #12

Max Range: 1.6807. Min Range: -1.6807

Max Act: 1.1548. Min Act: -0.0000

Data Index: 1357421 (The Pile)

Max Activating Token Index: 262

Text #13

Max Range: 1.6807. Min Range: -1.6807

Max Act: 1.1676. Min Act: -0.0000

Data Index: 1239666 (The Pile)

Max Activating Token Index: 274

Text #14

Max Range: 1.6807. Min Range: -1.6807

Max Act: 1.1970. Min Act: -0.0000

Data Index: 569357 (The Pile)

Max Activating Token Index: 694

Text #15

Max Range: 1.6807. Min Range: -1.6807

Max Act: 0.9930. Min Act: -0.0000

Data Index: 1371587 (The Pile)

Max Activating Token Index: 925

Text #16

Max Range: 1.6807. Min Range: -1.6807

Max Act: 1.1688. Min Act: -0.0000

Data Index: 372397 (The Pile)

Max Activating Token Index: 94

Text #17

Max Range: 1.6807. Min Range: -1.6807

Max Act: 1.0884. Min Act: -0.0000

Data Index: 1156110 (The Pile)

Max Activating Token Index: 582

Text #18

Max Range: 1.6807. Min Range: -1.6807

Max Act: 1.0186. Min Act: -0.0000

Data Index: 724592 (The Pile)

Max Activating Token Index: 711

Text #19

Max Range: 1.6807. Min Range: -1.6807

Max Act: 1.1811. Min Act: -0.0000

Data Index: 1893995 (The Pile)

Max Activating Token Index: 720