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

Dataset: The Pile

Neuron 1300 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: 0.6340. Min Range: -0.6340

Max Act: 0.6340. Min Act: -0.0000

Data Index: 818189 (The Pile)

Max Activating Token Index: 440

Text #1

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.6152. Min Act: -0.0000

Data Index: 72479 (The Pile)

Max Activating Token Index: 378

Text #2

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.4680. Min Act: -0.0000

Data Index: 979135 (The Pile)

Max Activating Token Index: 998

Text #3

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.5344. Min Act: -0.0000

Data Index: 1034828 (The Pile)

Max Activating Token Index: 519

Text #4

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.5151. Min Act: -0.0000

Data Index: 8023 (The Pile)

Max Activating Token Index: 782

Text #5

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.4833. Min Act: -0.0000

Data Index: 1526423 (The Pile)

Max Activating Token Index: 747

Text #6

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.4736. Min Act: -0.0000

Data Index: 1006625 (The Pile)

Max Activating Token Index: 851

Text #7

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.4635. Min Act: -0.0000

Data Index: 825136 (The Pile)

Max Activating Token Index: 897

Text #8

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.5178. Min Act: -0.0000

Data Index: 246821 (The Pile)

Max Activating Token Index: 23

Text #9

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.5178. Min Act: -0.0000

Data Index: 1621553 (The Pile)

Max Activating Token Index: 23

Text #10

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.5238. Min Act: -0.0000

Data Index: 1794131 (The Pile)

Max Activating Token Index: 835

Text #11

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.4714. Min Act: -0.0000

Data Index: 1789716 (The Pile)

Max Activating Token Index: 862

Text #12

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.4690. Min Act: -0.0000

Data Index: 304552 (The Pile)

Max Activating Token Index: 776

Text #13

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.4264. Min Act: -0.0000

Data Index: 1612667 (The Pile)

Max Activating Token Index: 844

Text #14

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.4807. Min Act: -0.0000

Data Index: 689767 (The Pile)

Max Activating Token Index: 884

Text #15

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.4390. Min Act: -0.0000

Data Index: 1916062 (The Pile)

Max Activating Token Index: 815

Text #16

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.4623. Min Act: -0.0000

Data Index: 225823 (The Pile)

Max Activating Token Index: 870

Text #17

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.4827. Min Act: -0.0000

Data Index: 1777535 (The Pile)

Max Activating Token Index: 991

Text #18

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.4805. Min Act: -0.0000

Data Index: 1231151 (The Pile)

Max Activating Token Index: 941

Text #19

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.4156. Min Act: -0.0000

Data Index: 1245968 (The Pile)

Max Activating Token Index: 696