Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3047 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2618. Min Range: -1.2618

Max Act: 1.2618. Min Act: -0.0000

Data Index: 1458386 (The Pile)

Max Activating Token Index: 175

Text #1

Max Range: 1.2618. Min Range: -1.2618

Max Act: 1.1230. Min Act: -0.0000

Data Index: 458688 (The Pile)

Max Activating Token Index: 517

Text #2

Max Range: 1.2618. Min Range: -1.2618

Max Act: 1.1499. Min Act: -0.0000

Data Index: 901751 (The Pile)

Max Activating Token Index: 870

Text #3

Max Range: 1.2618. Min Range: -1.2618

Max Act: 1.0782. Min Act: -0.0000

Data Index: 1552213 (The Pile)

Max Activating Token Index: 686

Text #4

Max Range: 1.2618. Min Range: -1.2618

Max Act: 1.0246. Min Act: -0.0000

Data Index: 532883 (The Pile)

Max Activating Token Index: 327

Text #5

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.9681. Min Act: -0.0000

Data Index: 1709158 (The Pile)

Max Activating Token Index: 329

Text #6

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.9278. Min Act: -0.0000

Data Index: 1659615 (The Pile)

Max Activating Token Index: 680

Text #7

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.9451. Min Act: -0.0000

Data Index: 508726 (The Pile)

Max Activating Token Index: 410

Text #8

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.9666. Min Act: -0.0000

Data Index: 1450747 (The Pile)

Max Activating Token Index: 674

Text #9

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.9642. Min Act: -0.0000

Data Index: 1467106 (The Pile)

Max Activating Token Index: 226

Text #10

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.9095. Min Act: -0.0000

Data Index: 729623 (The Pile)

Max Activating Token Index: 476

Text #11

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.9354. Min Act: -0.0000

Data Index: 1772555 (The Pile)

Max Activating Token Index: 451

Text #12

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.9328. Min Act: -0.0000

Data Index: 989806 (The Pile)

Max Activating Token Index: 127

Text #13

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.9583. Min Act: -0.0000

Data Index: 1761814 (The Pile)

Max Activating Token Index: 52

Text #14

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.8598. Min Act: -0.0000

Data Index: 842366 (The Pile)

Max Activating Token Index: 783

Text #15

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.8785. Min Act: -0.0000

Data Index: 695686 (The Pile)

Max Activating Token Index: 494

Text #16

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.8023. Min Act: -0.0000

Data Index: 1335031 (The Pile)

Max Activating Token Index: 998

Text #17

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.9151. Min Act: -0.0000

Data Index: 713135 (The Pile)

Max Activating Token Index: 595

Text #18

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.8242. Min Act: -0.0000

Data Index: 13681 (The Pile)

Max Activating Token Index: 1019

Text #19

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.9169. Min Act: -0.0000

Data Index: 707930 (The Pile)

Max Activating Token Index: 527