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

Dataset: The Pile

Neuron 4958 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0506. Min Range: -1.0506

Max Act: 1.0411. Min Act: -0.0000

Data Index: 417324 (The Pile)

Max Activating Token Index: 580

Text #1

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.9851. Min Act: -0.0000

Data Index: 1468162 (The Pile)

Max Activating Token Index: 307

Text #2

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.9704. Min Act: -0.0000

Data Index: 529915 (The Pile)

Max Activating Token Index: 655

Text #3

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.9920. Min Act: -0.0000

Data Index: 577906 (The Pile)

Max Activating Token Index: 908

Text #4

Max Range: 1.0506. Min Range: -1.0506

Max Act: 1.0506. Min Act: -0.0000

Data Index: 1167379 (The Pile)

Max Activating Token Index: 608

Text #5

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.9428. Min Act: -0.0000

Data Index: 988498 (The Pile)

Max Activating Token Index: 956

Text #6

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.9816. Min Act: -0.0000

Data Index: 432364 (The Pile)

Max Activating Token Index: 883

Text #7

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.9428. Min Act: -0.0000

Data Index: 626384 (The Pile)

Max Activating Token Index: 623

Text #8

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.9295. Min Act: -0.0000

Data Index: 1293482 (The Pile)

Max Activating Token Index: 732

Text #9

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.9307. Min Act: -0.0000

Data Index: 1147626 (The Pile)

Max Activating Token Index: 454

Text #10

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.9632. Min Act: -0.0000

Data Index: 933728 (The Pile)

Max Activating Token Index: 14

Text #11

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.9475. Min Act: -0.0000

Data Index: 523862 (The Pile)

Max Activating Token Index: 151

Text #12

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.9223. Min Act: -0.0000

Data Index: 876570 (The Pile)

Max Activating Token Index: 579

Text #13

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.9478. Min Act: -0.0000

Data Index: 906145 (The Pile)

Max Activating Token Index: 178

Text #14

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.8944. Min Act: -0.0000

Data Index: 470779 (The Pile)

Max Activating Token Index: 990

Text #15

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.8808. Min Act: -0.0000

Data Index: 869355 (The Pile)

Max Activating Token Index: 177

Text #16

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.9028. Min Act: -0.0000

Data Index: 674927 (The Pile)

Max Activating Token Index: 603

Text #17

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.8976. Min Act: -0.0000

Data Index: 412548 (The Pile)

Max Activating Token Index: 222

Text #18

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.8652. Min Act: -0.0000

Data Index: 630888 (The Pile)

Max Activating Token Index: 88

Text #19

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.8531. Min Act: -0.0000

Data Index: 1658234 (The Pile)

Max Activating Token Index: 6