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

Dataset: The Pile

Neuron 4795 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5766. Min Range: -1.5766

Max Act: 1.5766. Min Act: -0.0000

Data Index: 1992122 (The Pile)

Max Activating Token Index: 326

Text #1

Max Range: 1.5766. Min Range: -1.5766

Max Act: 1.1692. Min Act: -0.0000

Data Index: 1510222 (The Pile)

Max Activating Token Index: 89

Text #2

Max Range: 1.5766. Min Range: -1.5766

Max Act: 1.1474. Min Act: -0.0000

Data Index: 655450 (The Pile)

Max Activating Token Index: 472

Text #3

Max Range: 1.5766. Min Range: -1.5766

Max Act: 0.9839. Min Act: -0.0000

Data Index: 361096 (The Pile)

Max Activating Token Index: 206

Text #4

Max Range: 1.5766. Min Range: -1.5766

Max Act: 1.0306. Min Act: -0.0000

Data Index: 644413 (The Pile)

Max Activating Token Index: 519

Text #5

Max Range: 1.5766. Min Range: -1.5766

Max Act: 1.0035. Min Act: -0.0000

Data Index: 1827423 (The Pile)

Max Activating Token Index: 806

Text #6

Max Range: 1.5766. Min Range: -1.5766

Max Act: 0.9903. Min Act: -0.0000

Data Index: 633293 (The Pile)

Max Activating Token Index: 561

Text #7

Max Range: 1.5766. Min Range: -1.5766

Max Act: 0.9806. Min Act: -0.0000

Data Index: 798466 (The Pile)

Max Activating Token Index: 855

Text #8

Max Range: 1.5766. Min Range: -1.5766

Max Act: 0.9218. Min Act: -0.0000

Data Index: 539220 (The Pile)

Max Activating Token Index: 198

Text #9

Max Range: 1.5766. Min Range: -1.5766

Max Act: 0.9054. Min Act: -0.0000

Data Index: 1094550 (The Pile)

Max Activating Token Index: 791

Text #10

Max Range: 1.5766. Min Range: -1.5766

Max Act: 0.9666. Min Act: -0.0000

Data Index: 1635715 (The Pile)

Max Activating Token Index: 845

Text #11

Max Range: 1.5766. Min Range: -1.5766

Max Act: 0.9429. Min Act: -0.0000

Data Index: 616797 (The Pile)

Max Activating Token Index: 238

Text #12

Max Range: 1.5766. Min Range: -1.5766

Max Act: 0.9081. Min Act: -0.0000

Data Index: 1567009 (The Pile)

Max Activating Token Index: 411

Text #13

Max Range: 1.5766. Min Range: -1.5766

Max Act: 0.9572. Min Act: -0.0000

Data Index: 1760681 (The Pile)

Max Activating Token Index: 226

Text #14

Max Range: 1.5766. Min Range: -1.5766

Max Act: 0.9469. Min Act: -0.0000

Data Index: 688524 (The Pile)

Max Activating Token Index: 262

Text #15

Max Range: 1.5766. Min Range: -1.5766

Max Act: 0.8742. Min Act: 0.0000

Data Index: 1600831 (The Pile)

Max Activating Token Index: 397

Text #16

Max Range: 1.5766. Min Range: -1.5766

Max Act: 0.8707. Min Act: -0.0000

Data Index: 735878 (The Pile)

Max Activating Token Index: 430

Text #17

Max Range: 1.5766. Min Range: -1.5766

Max Act: 0.8656. Min Act: -0.0000

Data Index: 372406 (The Pile)

Max Activating Token Index: 752

Text #18

Max Range: 1.5766. Min Range: -1.5766

Max Act: 0.8233. Min Act: 0.0000

Data Index: 1742046 (The Pile)

Max Activating Token Index: 959

Text #19

Max Range: 1.5766. Min Range: -1.5766

Max Act: 0.8596. Min Act: -0.0000

Data Index: 60368 (The Pile)

Max Activating Token Index: 783