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

Dataset: The Pile

Neuron 2564 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: 1.4736. Min Range: -1.4736

Max Act: 1.4736. Min Act: -0.0000

Data Index: 543893 (The Pile)

Max Activating Token Index: 776

Text #1

Max Range: 1.4736. Min Range: -1.4736

Max Act: 1.3950. Min Act: -0.0000

Data Index: 785765 (The Pile)

Max Activating Token Index: 605

Text #2

Max Range: 1.4736. Min Range: -1.4736

Max Act: 1.4417. Min Act: -0.0000

Data Index: 26191 (The Pile)

Max Activating Token Index: 710

Text #3

Max Range: 1.4736. Min Range: -1.4736

Max Act: 1.3028. Min Act: -0.0000

Data Index: 478469 (The Pile)

Max Activating Token Index: 949

Text #4

Max Range: 1.4736. Min Range: -1.4736

Max Act: 1.3481. Min Act: -0.0000

Data Index: 1550547 (The Pile)

Max Activating Token Index: 355

Text #5

Max Range: 1.4736. Min Range: -1.4736

Max Act: 1.3618. Min Act: -0.0000

Data Index: 590162 (The Pile)

Max Activating Token Index: 404

Text #6

Max Range: 1.4736. Min Range: -1.4736

Max Act: 1.2852. Min Act: -0.0000

Data Index: 1809998 (The Pile)

Max Activating Token Index: 1016

Text #7

Max Range: 1.4736. Min Range: -1.4736

Max Act: 1.3057. Min Act: -0.0000

Data Index: 1759732 (The Pile)

Max Activating Token Index: 481

Text #8

Max Range: 1.4736. Min Range: -1.4736

Max Act: 1.2920. Min Act: -0.0000

Data Index: 1278255 (The Pile)

Max Activating Token Index: 993

Text #9

Max Range: 1.4736. Min Range: -1.4736

Max Act: 1.3375. Min Act: -0.0000

Data Index: 1958966 (The Pile)

Max Activating Token Index: 749

Text #10

Max Range: 1.4736. Min Range: -1.4736

Max Act: 1.2206. Min Act: -0.0000

Data Index: 739206 (The Pile)

Max Activating Token Index: 914

Text #11

Max Range: 1.4736. Min Range: -1.4736

Max Act: 1.2078. Min Act: -0.0000

Data Index: 1743313 (The Pile)

Max Activating Token Index: 896

Text #12

Max Range: 1.4736. Min Range: -1.4736

Max Act: 1.1195. Min Act: -0.0000

Data Index: 516019 (The Pile)

Max Activating Token Index: 733

Text #13

Max Range: 1.4736. Min Range: -1.4736

Max Act: 1.2280. Min Act: -0.0000

Data Index: 1447313 (The Pile)

Max Activating Token Index: 806

Text #14

Max Range: 1.4736. Min Range: -1.4736

Max Act: 1.1388. Min Act: -0.0000

Data Index: 81649 (The Pile)

Max Activating Token Index: 1013

Text #15

Max Range: 1.4736. Min Range: -1.4736

Max Act: 1.2414. Min Act: -0.0000

Data Index: 966504 (The Pile)

Max Activating Token Index: 537

Text #16

Max Range: 1.4736. Min Range: -1.4736

Max Act: 1.0867. Min Act: -0.0000

Data Index: 1326337 (The Pile)

Max Activating Token Index: 471

Text #17

Max Range: 1.4736. Min Range: -1.4736

Max Act: 1.1443. Min Act: -0.0000

Data Index: 969967 (The Pile)

Max Activating Token Index: 951

Text #18

Max Range: 1.4736. Min Range: -1.4736

Max Act: 1.0813. Min Act: -0.0000

Data Index: 868095 (The Pile)

Max Activating Token Index: 888

Text #19

Max Range: 1.4736. Min Range: -1.4736

Max Act: 1.0465. Min Act: -0.0000

Data Index: 591542 (The Pile)

Max Activating Token Index: 534