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

Dataset: The Pile

Neuron 3675 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: 3.1851. Min Range: -3.1851

Max Act: 2.8740. Min Act: -0.0000

Data Index: 536635 (The Pile)

Max Activating Token Index: 636

Text #1

Max Range: 3.1851. Min Range: -3.1851

Max Act: 3.0548. Min Act: -0.0000

Data Index: 1236242 (The Pile)

Max Activating Token Index: 387

Text #2

Max Range: 3.1851. Min Range: -3.1851

Max Act: 3.1851. Min Act: -0.0000

Data Index: 738719 (The Pile)

Max Activating Token Index: 487

Text #3

Max Range: 3.1851. Min Range: -3.1851

Max Act: 2.8808. Min Act: -0.0000

Data Index: 994938 (The Pile)

Max Activating Token Index: 662

Text #4

Max Range: 3.1851. Min Range: -3.1851

Max Act: 2.8624. Min Act: -0.0000

Data Index: 1166456 (The Pile)

Max Activating Token Index: 494

Text #5

Max Range: 3.1851. Min Range: -3.1851

Max Act: 3.0836. Min Act: -0.0000

Data Index: 81986 (The Pile)

Max Activating Token Index: 471

Text #6

Max Range: 3.1851. Min Range: -3.1851

Max Act: 3.0905. Min Act: -0.0000

Data Index: 1542391 (The Pile)

Max Activating Token Index: 439

Text #7

Max Range: 3.1851. Min Range: -3.1851

Max Act: 2.6159. Min Act: -0.0000

Data Index: 1159618 (The Pile)

Max Activating Token Index: 663

Text #8

Max Range: 3.1851. Min Range: -3.1851

Max Act: 3.0107. Min Act: -0.0000

Data Index: 843781 (The Pile)

Max Activating Token Index: 594

Text #9

Max Range: 3.1851. Min Range: -3.1851

Max Act: 2.7514. Min Act: -0.0000

Data Index: 717852 (The Pile)

Max Activating Token Index: 732

Text #10

Max Range: 3.1851. Min Range: -3.1851

Max Act: 3.0056. Min Act: -0.0000

Data Index: 691158 (The Pile)

Max Activating Token Index: 463

Text #11

Max Range: 3.1851. Min Range: -3.1851

Max Act: 2.7603. Min Act: -0.0000

Data Index: 1588368 (The Pile)

Max Activating Token Index: 90

Text #12

Max Range: 3.1851. Min Range: -3.1851

Max Act: 2.9264. Min Act: -0.0000

Data Index: 197974 (The Pile)

Max Activating Token Index: 119

Text #13

Max Range: 3.1851. Min Range: -3.1851

Max Act: 2.7488. Min Act: -0.0000

Data Index: 1087954 (The Pile)

Max Activating Token Index: 362

Text #14

Max Range: 3.1851. Min Range: -3.1851

Max Act: 2.5992. Min Act: -0.0000

Data Index: 493219 (The Pile)

Max Activating Token Index: 580

Text #15

Max Range: 3.1851. Min Range: -3.1851

Max Act: 2.8711. Min Act: -0.0000

Data Index: 110045 (The Pile)

Max Activating Token Index: 433

Text #16

Max Range: 3.1851. Min Range: -3.1851

Max Act: 2.6792. Min Act: -0.0000

Data Index: 1339067 (The Pile)

Max Activating Token Index: 453

Text #17

Max Range: 3.1851. Min Range: -3.1851

Max Act: 2.7129. Min Act: -0.0000

Data Index: 1052992 (The Pile)

Max Activating Token Index: 598

Text #18

Max Range: 3.1851. Min Range: -3.1851

Max Act: 2.6966. Min Act: -0.0000

Data Index: 625314 (The Pile)

Max Activating Token Index: 452

Text #19

Max Range: 3.1851. Min Range: -3.1851

Max Act: 2.8046. Min Act: -0.0000

Data Index: 1135355 (The Pile)

Max Activating Token Index: 378