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

Dataset: The Pile

Neuron 2232 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2714. Min Range: -1.2714

Max Act: 1.2714. Min Act: -0.0000

Data Index: 134414 (The Pile)

Max Activating Token Index: 737

Text #1

Max Range: 1.2714. Min Range: -1.2714

Max Act: 1.1180. Min Act: -0.0000

Data Index: 1026935 (The Pile)

Max Activating Token Index: 989

Text #2

Max Range: 1.2714. Min Range: -1.2714

Max Act: 1.1773. Min Act: -0.0000

Data Index: 1138079 (The Pile)

Max Activating Token Index: 537

Text #3

Max Range: 1.2714. Min Range: -1.2714

Max Act: 1.0920. Min Act: -0.0000

Data Index: 831306 (The Pile)

Max Activating Token Index: 800

Text #4

Max Range: 1.2714. Min Range: -1.2714

Max Act: 1.1077. Min Act: -0.0000

Data Index: 133110 (The Pile)

Max Activating Token Index: 595

Text #5

Max Range: 1.2714. Min Range: -1.2714

Max Act: 1.0430. Min Act: -0.0000

Data Index: 1359779 (The Pile)

Max Activating Token Index: 744

Text #6

Max Range: 1.2714. Min Range: -1.2714

Max Act: 1.1064. Min Act: -0.0000

Data Index: 1110654 (The Pile)

Max Activating Token Index: 25

Text #7

Max Range: 1.2714. Min Range: -1.2714

Max Act: 0.9689. Min Act: -0.0000

Data Index: 1087342 (The Pile)

Max Activating Token Index: 789

Text #8

Max Range: 1.2714. Min Range: -1.2714

Max Act: 0.9930. Min Act: -0.0000

Data Index: 563276 (The Pile)

Max Activating Token Index: 41

Text #9

Max Range: 1.2714. Min Range: -1.2714

Max Act: 0.9786. Min Act: -0.0000

Data Index: 995725 (The Pile)

Max Activating Token Index: 440

Text #10

Max Range: 1.2714. Min Range: -1.2714

Max Act: 0.9718. Min Act: -0.0000

Data Index: 750396 (The Pile)

Max Activating Token Index: 766

Text #11

Max Range: 1.2714. Min Range: -1.2714

Max Act: 0.9005. Min Act: -0.0000

Data Index: 1609395 (The Pile)

Max Activating Token Index: 210

Text #12

Max Range: 1.2714. Min Range: -1.2714

Max Act: 0.8377. Min Act: -0.0000

Data Index: 995283 (The Pile)

Max Activating Token Index: 922

Text #13

Max Range: 1.2714. Min Range: -1.2714

Max Act: 0.8940. Min Act: -0.0000

Data Index: 958958 (The Pile)

Max Activating Token Index: 931

Text #14

Max Range: 1.2714. Min Range: -1.2714

Max Act: 0.8790. Min Act: -0.0000

Data Index: 379226 (The Pile)

Max Activating Token Index: 796

Text #15

Max Range: 1.2714. Min Range: -1.2714

Max Act: 0.9152. Min Act: -0.0000

Data Index: 660604 (The Pile)

Max Activating Token Index: 87

Text #16

Max Range: 1.2714. Min Range: -1.2714

Max Act: 0.8517. Min Act: -0.0000

Data Index: 1695539 (The Pile)

Max Activating Token Index: 750

Text #17

Max Range: 1.2714. Min Range: -1.2714

Max Act: 0.8894. Min Act: -0.0000

Data Index: 202631 (The Pile)

Max Activating Token Index: 635

Text #18

Max Range: 1.2714. Min Range: -1.2714

Max Act: 0.7932. Min Act: -0.0000

Data Index: 1910041 (The Pile)

Max Activating Token Index: 200

Text #19

Max Range: 1.2714. Min Range: -1.2714

Max Act: 0.8362. Min Act: -0.0000

Data Index: 915351 (The Pile)

Max Activating Token Index: 387