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

Dataset: The Pile

Neuron 1473 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.5851. Min Act: -0.0000

Data Index: 1468955 (The Pile)

Max Activating Token Index: 82

Text #1

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.5203. Min Act: -0.0000

Data Index: 692216 (The Pile)

Max Activating Token Index: 855

Text #2

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.5333. Min Act: -0.0000

Data Index: 118399 (The Pile)

Max Activating Token Index: 76

Text #3

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.5537. Min Act: -0.0000

Data Index: 1443988 (The Pile)

Max Activating Token Index: 973

Text #4

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.4784. Min Act: -0.0000

Data Index: 293719 (The Pile)

Max Activating Token Index: 447

Text #5

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.4479. Min Act: -0.0000

Data Index: 1940196 (The Pile)

Max Activating Token Index: 618

Text #6

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.5519. Min Act: -0.0000

Data Index: 1292135 (The Pile)

Max Activating Token Index: 479

Text #7

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.4741. Min Act: -0.0000

Data Index: 994125 (The Pile)

Max Activating Token Index: 164

Text #8

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.3439. Min Act: -0.0000

Data Index: 1673216 (The Pile)

Max Activating Token Index: 175

Text #9

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.4109. Min Act: -0.0000

Data Index: 299117 (The Pile)

Max Activating Token Index: 386

Text #10

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.2989. Min Act: -0.0000

Data Index: 706619 (The Pile)

Max Activating Token Index: 961

Text #11

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.3719. Min Act: -0.0000

Data Index: 1292316 (The Pile)

Max Activating Token Index: 712

Text #12

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.4012. Min Act: -0.0000

Data Index: 766284 (The Pile)

Max Activating Token Index: 119

Text #13

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.3974. Min Act: -0.0000

Data Index: 1692072 (The Pile)

Max Activating Token Index: 850

Text #14

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.4186. Min Act: -0.0000

Data Index: 1978284 (The Pile)

Max Activating Token Index: 450

Text #15

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.3645. Min Act: -0.0000

Data Index: 772411 (The Pile)

Max Activating Token Index: 466

Text #16

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.3560. Min Act: -0.0000

Data Index: 289993 (The Pile)

Max Activating Token Index: 650

Text #17

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.3807. Min Act: -0.0000

Data Index: 434123 (The Pile)

Max Activating Token Index: 136

Text #18

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.3693. Min Act: -0.0000

Data Index: 1624950 (The Pile)

Max Activating Token Index: 373

Text #19

Max Range: 0.5851. Min Range: -0.5851

Max Act: 0.3732. Min Act: -0.0000

Data Index: 1298294 (The Pile)

Max Activating Token Index: 313