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

Dataset: The Pile

Neuron 1482 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: 0.6569. Min Range: -0.6569

Max Act: 0.6569. Min Act: -0.0000

Data Index: 1717948 (The Pile)

Max Activating Token Index: 662

Text #1

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.6370. Min Act: -0.0000

Data Index: 1178775 (The Pile)

Max Activating Token Index: 348

Text #2

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.6320. Min Act: -0.0000

Data Index: 1627184 (The Pile)

Max Activating Token Index: 771

Text #3

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.5909. Min Act: -0.0000

Data Index: 359466 (The Pile)

Max Activating Token Index: 673

Text #4

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.6280. Min Act: -0.0000

Data Index: 798192 (The Pile)

Max Activating Token Index: 869

Text #5

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.5792. Min Act: 0.0000

Data Index: 604406 (The Pile)

Max Activating Token Index: 854

Text #6

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.5869. Min Act: -0.0000

Data Index: 986023 (The Pile)

Max Activating Token Index: 518

Text #7

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.5667. Min Act: -0.0000

Data Index: 1104701 (The Pile)

Max Activating Token Index: 599

Text #8

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.5661. Min Act: -0.0000

Data Index: 905516 (The Pile)

Max Activating Token Index: 326

Text #9

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.5789. Min Act: -0.0000

Data Index: 437257 (The Pile)

Max Activating Token Index: 908

Text #10

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.5462. Min Act: 0.0000

Data Index: 1796769 (The Pile)

Max Activating Token Index: 141

Text #11

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.5416. Min Act: -0.0000

Data Index: 635349 (The Pile)

Max Activating Token Index: 453

Text #12

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.5449. Min Act: -0.0000

Data Index: 1063164 (The Pile)

Max Activating Token Index: 746

Text #13

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.5041. Min Act: -0.0000

Data Index: 934480 (The Pile)

Max Activating Token Index: 583

Text #14

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.5190. Min Act: -0.0000

Data Index: 1187676 (The Pile)

Max Activating Token Index: 187

Text #15

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.5141. Min Act: -0.0000

Data Index: 1345937 (The Pile)

Max Activating Token Index: 147

Text #16

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.5455. Min Act: -0.0000

Data Index: 1536590 (The Pile)

Max Activating Token Index: 128

Text #17

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.5147. Min Act: -0.0000

Data Index: 175927 (The Pile)

Max Activating Token Index: 723

Text #18

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.5102. Min Act: -0.0000

Data Index: 1560107 (The Pile)

Max Activating Token Index: 356

Text #19

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.4769. Min Act: -0.0000

Data Index: 121105 (The Pile)

Max Activating Token Index: 616