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

Dataset: The Pile

Neuron 724 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.8403. Min Act: -0.0000

Data Index: 1456615 (The Pile)

Max Activating Token Index: 510

Text #1

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.7750. Min Act: -0.0000

Data Index: 1894085 (The Pile)

Max Activating Token Index: 912

Text #2

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.6048. Min Act: -0.0000

Data Index: 1462932 (The Pile)

Max Activating Token Index: 884

Text #3

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.6199. Min Act: -0.0000

Data Index: 206537 (The Pile)

Max Activating Token Index: 129

Text #4

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.5222. Min Act: -0.0000

Data Index: 1205428 (The Pile)

Max Activating Token Index: 781

Text #5

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.4747. Min Act: -0.0000

Data Index: 270840 (The Pile)

Max Activating Token Index: 916

Text #6

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.5330. Min Act: -0.0000

Data Index: 961619 (The Pile)

Max Activating Token Index: 585

Text #7

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.5609. Min Act: -0.0000

Data Index: 415062 (The Pile)

Max Activating Token Index: 102

Text #8

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.4162. Min Act: -0.0000

Data Index: 586839 (The Pile)

Max Activating Token Index: 412

Text #9

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.4756. Min Act: -0.0000

Data Index: 1775540 (The Pile)

Max Activating Token Index: 774

Text #10

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.2683. Min Act: -0.0000

Data Index: 392723 (The Pile)

Max Activating Token Index: 708

Text #11

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.2913. Min Act: -0.0000

Data Index: 549183 (The Pile)

Max Activating Token Index: 395

Text #12

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.3322. Min Act: -0.0000

Data Index: 695942 (The Pile)

Max Activating Token Index: 369

Text #13

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.1903. Min Act: -0.0000

Data Index: 86028 (The Pile)

Max Activating Token Index: 468

Text #14

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.1847. Min Act: -0.0000

Data Index: 1373403 (The Pile)

Max Activating Token Index: 287

Text #15

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.2374. Min Act: -0.0000

Data Index: 1397006 (The Pile)

Max Activating Token Index: 510

Text #16

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.1576. Min Act: 0.0000

Data Index: 56450 (The Pile)

Max Activating Token Index: 679

Text #17

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.0807. Min Act: -0.0000

Data Index: 107222 (The Pile)

Max Activating Token Index: 689

Text #18

Max Range: 1.8403. Min Range: -1.8403

Max Act: 0.9880. Min Act: -0.0000

Data Index: 1762659 (The Pile)

Max Activating Token Index: 978

Text #19

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.0472. Min Act: 0.0000

Data Index: 962098 (The Pile)

Max Activating Token Index: 496