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

Dataset: The Pile

Neuron 487 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: 0.8863. Min Range: -0.8863

Max Act: 0.8863. Min Act: -0.0000

Data Index: 273409 (The Pile)

Max Activating Token Index: 514

Text #1

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.7796. Min Act: -0.0000

Data Index: 1809933 (The Pile)

Max Activating Token Index: 699

Text #2

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.5955. Min Act: -0.0000

Data Index: 512394 (The Pile)

Max Activating Token Index: 658

Text #3

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.6823. Min Act: -0.0000

Data Index: 1640594 (The Pile)

Max Activating Token Index: 400

Text #4

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.6602. Min Act: -0.0000

Data Index: 1835910 (The Pile)

Max Activating Token Index: 689

Text #5

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.5946. Min Act: -0.0000

Data Index: 744538 (The Pile)

Max Activating Token Index: 764

Text #6

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.6329. Min Act: -0.0000

Data Index: 1248146 (The Pile)

Max Activating Token Index: 879

Text #7

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.6867. Min Act: -0.0000

Data Index: 206791 (The Pile)

Max Activating Token Index: 700

Text #8

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.6801. Min Act: -0.0000

Data Index: 1502164 (The Pile)

Max Activating Token Index: 121

Text #9

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.6731. Min Act: -0.0000

Data Index: 1767184 (The Pile)

Max Activating Token Index: 479

Text #10

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.5609. Min Act: -0.0000

Data Index: 788444 (The Pile)

Max Activating Token Index: 503

Text #11

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.5867. Min Act: -0.0000

Data Index: 1049645 (The Pile)

Max Activating Token Index: 830

Text #12

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.5665. Min Act: -0.0000

Data Index: 1307317 (The Pile)

Max Activating Token Index: 823

Text #13

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.5533. Min Act: -0.0000

Data Index: 1520412 (The Pile)

Max Activating Token Index: 397

Text #14

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.4576. Min Act: -0.0000

Data Index: 1339082 (The Pile)

Max Activating Token Index: 935

Text #15

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.5186. Min Act: -0.0000

Data Index: 1296953 (The Pile)

Max Activating Token Index: 400

Text #16

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.4844. Min Act: 0.0000

Data Index: 1596355 (The Pile)

Max Activating Token Index: 150

Text #17

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.4826. Min Act: -0.0000

Data Index: 1747318 (The Pile)

Max Activating Token Index: 56

Text #18

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.4747. Min Act: -0.0000

Data Index: 1994266 (The Pile)

Max Activating Token Index: 670

Text #19

Max Range: 0.8863. Min Range: -0.8863

Max Act: 0.5223. Min Act: -0.0000

Data Index: 1002062 (The Pile)

Max Activating Token Index: 827