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

Dataset: The Pile

Neuron 3291 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: 1.7627. Min Range: -1.7627

Max Act: 1.7245. Min Act: -0.0000

Data Index: 1938251 (The Pile)

Max Activating Token Index: 656

Text #1

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.5833. Min Act: -0.0000

Data Index: 11929 (The Pile)

Max Activating Token Index: 1012

Text #2

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.7627. Min Act: -0.0000

Data Index: 1934314 (The Pile)

Max Activating Token Index: 958

Text #3

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.7420. Min Act: -0.0000

Data Index: 1214318 (The Pile)

Max Activating Token Index: 709

Text #4

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.6456. Min Act: -0.0000

Data Index: 795144 (The Pile)

Max Activating Token Index: 605

Text #5

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.6239. Min Act: -0.0000

Data Index: 964698 (The Pile)

Max Activating Token Index: 578

Text #6

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.6267. Min Act: -0.0000

Data Index: 270688 (The Pile)

Max Activating Token Index: 642

Text #7

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.5940. Min Act: -0.0000

Data Index: 1824021 (The Pile)

Max Activating Token Index: 902

Text #8

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.6764. Min Act: -0.0000

Data Index: 576209 (The Pile)

Max Activating Token Index: 896

Text #9

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.5802. Min Act: -0.0000

Data Index: 1601461 (The Pile)

Max Activating Token Index: 842

Text #10

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.6633. Min Act: -0.0000

Data Index: 1007953 (The Pile)

Max Activating Token Index: 630

Text #11

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.6655. Min Act: -0.0000

Data Index: 392137 (The Pile)

Max Activating Token Index: 861

Text #12

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.7576. Min Act: -0.0000

Data Index: 1541831 (The Pile)

Max Activating Token Index: 553

Text #13

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.5647. Min Act: -0.0000

Data Index: 1037575 (The Pile)

Max Activating Token Index: 468

Text #14

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.5531. Min Act: -0.0000

Data Index: 1915119 (The Pile)

Max Activating Token Index: 758

Text #15

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.7483. Min Act: -0.0000

Data Index: 1114642 (The Pile)

Max Activating Token Index: 627

Text #16

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.5657. Min Act: -0.0000

Data Index: 1170888 (The Pile)

Max Activating Token Index: 722

Text #17

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.6469. Min Act: -0.0000

Data Index: 824214 (The Pile)

Max Activating Token Index: 505

Text #18

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.6500. Min Act: -0.0000

Data Index: 186457 (The Pile)

Max Activating Token Index: 634

Text #19

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.5504. Min Act: -0.0000

Data Index: 34488 (The Pile)

Max Activating Token Index: 523