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

Dataset: The Pile

Neuron 3519 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: 3.3746. Min Range: -3.3746

Max Act: 3.3746. Min Act: -0.0000

Data Index: 1022640 (The Pile)

Max Activating Token Index: 264

Text #1

Max Range: 3.3746. Min Range: -3.3746

Max Act: 3.2801. Min Act: -0.0000

Data Index: 1546714 (The Pile)

Max Activating Token Index: 985

Text #2

Max Range: 3.3746. Min Range: -3.3746

Max Act: 2.6846. Min Act: -0.0000

Data Index: 1529990 (The Pile)

Max Activating Token Index: 56

Text #3

Max Range: 3.3746. Min Range: -3.3746

Max Act: 3.0140. Min Act: -0.0000

Data Index: 1992795 (The Pile)

Max Activating Token Index: 791

Text #4

Max Range: 3.3746. Min Range: -3.3746

Max Act: 2.6438. Min Act: -0.0000

Data Index: 427692 (The Pile)

Max Activating Token Index: 104

Text #5

Max Range: 3.3746. Min Range: -3.3746

Max Act: 2.7782. Min Act: -0.0000

Data Index: 1152662 (The Pile)

Max Activating Token Index: 52

Text #6

Max Range: 3.3746. Min Range: -3.3746

Max Act: 2.4950. Min Act: -0.0000

Data Index: 360504 (The Pile)

Max Activating Token Index: 13

Text #7

Max Range: 3.3746. Min Range: -3.3746

Max Act: 2.4834. Min Act: -0.0000

Data Index: 1157587 (The Pile)

Max Activating Token Index: 327

Text #8

Max Range: 3.3746. Min Range: -3.3746

Max Act: 2.3194. Min Act: -0.0000

Data Index: 1006967 (The Pile)

Max Activating Token Index: 395

Text #9

Max Range: 3.3746. Min Range: -3.3746

Max Act: 2.3504. Min Act: -0.0000

Data Index: 1482311 (The Pile)

Max Activating Token Index: 606

Text #10

Max Range: 3.3746. Min Range: -3.3746

Max Act: 2.4283. Min Act: -0.0000

Data Index: 307800 (The Pile)

Max Activating Token Index: 395

Text #11

Max Range: 3.3746. Min Range: -3.3746

Max Act: 2.4260. Min Act: -0.0000

Data Index: 434746 (The Pile)

Max Activating Token Index: 956

Text #12

Max Range: 3.3746. Min Range: -3.3746

Max Act: 2.4140. Min Act: -0.0000

Data Index: 197565 (The Pile)

Max Activating Token Index: 455

Text #13

Max Range: 3.3746. Min Range: -3.3746

Max Act: 2.3161. Min Act: -0.0000

Data Index: 1572836 (The Pile)

Max Activating Token Index: 257

Text #14

Max Range: 3.3746. Min Range: -3.3746

Max Act: 2.1108. Min Act: -0.0000

Data Index: 390440 (The Pile)

Max Activating Token Index: 291

Text #15

Max Range: 3.3746. Min Range: -3.3746

Max Act: 2.0977. Min Act: -0.0000

Data Index: 966117 (The Pile)

Max Activating Token Index: 597

Text #16

Max Range: 3.3746. Min Range: -3.3746

Max Act: 2.2385. Min Act: -0.0000

Data Index: 1717622 (The Pile)

Max Activating Token Index: 34

Text #17

Max Range: 3.3746. Min Range: -3.3746

Max Act: 2.1022. Min Act: -0.0000

Data Index: 840759 (The Pile)

Max Activating Token Index: 796

Text #18

Max Range: 3.3746. Min Range: -3.3746

Max Act: 2.0646. Min Act: -0.0000

Data Index: 1340073 (The Pile)

Max Activating Token Index: 314

Text #19

Max Range: 3.3746. Min Range: -3.3746

Max Act: 2.2989. Min Act: -0.0000

Data Index: 847163 (The Pile)

Max Activating Token Index: 633