Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1279 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.9615. Min Act: -0.0000

Data Index: 691133 (The Pile)

Max Activating Token Index: 63

Text #1

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.8292. Min Act: -0.0000

Data Index: 1278731 (The Pile)

Max Activating Token Index: 531

Text #2

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.7670. Min Act: -0.0000

Data Index: 530058 (The Pile)

Max Activating Token Index: 731

Text #3

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.7637. Min Act: -0.0000

Data Index: 711726 (The Pile)

Max Activating Token Index: 463

Text #4

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.7817. Min Act: -0.0000

Data Index: 627481 (The Pile)

Max Activating Token Index: 227

Text #5

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.7136. Min Act: -0.0000

Data Index: 726978 (The Pile)

Max Activating Token Index: 850

Text #6

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.7135. Min Act: -0.0000

Data Index: 366379 (The Pile)

Max Activating Token Index: 789

Text #7

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.6373. Min Act: -0.0000

Data Index: 1342492 (The Pile)

Max Activating Token Index: 878

Text #8

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.6803. Min Act: -0.0000

Data Index: 1462311 (The Pile)

Max Activating Token Index: 482

Text #9

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.6297. Min Act: -0.0000

Data Index: 671470 (The Pile)

Max Activating Token Index: 560

Text #10

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.6684. Min Act: -0.0000

Data Index: 969907 (The Pile)

Max Activating Token Index: 16

Text #11

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.7519. Min Act: -0.0000

Data Index: 1934037 (The Pile)

Max Activating Token Index: 695

Text #12

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.6507. Min Act: -0.0000

Data Index: 1459495 (The Pile)

Max Activating Token Index: 549

Text #13

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.6856. Min Act: -0.0000

Data Index: 1716029 (The Pile)

Max Activating Token Index: 116

Text #14

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.6611. Min Act: -0.0000

Data Index: 1544803 (The Pile)

Max Activating Token Index: 597

Text #15

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.6520. Min Act: -0.0000

Data Index: 1888679 (The Pile)

Max Activating Token Index: 322

Text #16

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.6483. Min Act: -0.0000

Data Index: 913657 (The Pile)

Max Activating Token Index: 516

Text #17

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.6317. Min Act: -0.0000

Data Index: 1773747 (The Pile)

Max Activating Token Index: 907

Text #18

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.6040. Min Act: -0.0000

Data Index: 462063 (The Pile)

Max Activating Token Index: 328

Text #19

Max Range: 0.9615. Min Range: -0.9615

Max Act: 0.6232. Min Act: -0.0000

Data Index: 428096 (The Pile)

Max Activating Token Index: 497