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

Dataset: The Pile

Neuron 643 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: 0.5263. Min Range: -0.5263

Max Act: 0.5263. Min Act: -0.0000

Data Index: 21376 (The Pile)

Max Activating Token Index: 651

Text #1

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4651. Min Act: -0.0000

Data Index: 47660 (The Pile)

Max Activating Token Index: 930

Text #2

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4021. Min Act: -0.0000

Data Index: 1843459 (The Pile)

Max Activating Token Index: 627

Text #3

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3527. Min Act: -0.0000

Data Index: 1646026 (The Pile)

Max Activating Token Index: 722

Text #4

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3608. Min Act: -0.0000

Data Index: 1567650 (The Pile)

Max Activating Token Index: 774

Text #5

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3913. Min Act: -0.0000

Data Index: 1808588 (The Pile)

Max Activating Token Index: 789

Text #6

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3786. Min Act: -0.0000

Data Index: 66510 (The Pile)

Max Activating Token Index: 759

Text #7

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3291. Min Act: -0.0000

Data Index: 1042751 (The Pile)

Max Activating Token Index: 494

Text #8

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3420. Min Act: -0.0000

Data Index: 54608 (The Pile)

Max Activating Token Index: 933

Text #9

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.2758. Min Act: -0.0000

Data Index: 879462 (The Pile)

Max Activating Token Index: 790

Text #10

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3350. Min Act: -0.0000

Data Index: 1056617 (The Pile)

Max Activating Token Index: 676

Text #11

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3619. Min Act: -0.0000

Data Index: 183938 (The Pile)

Max Activating Token Index: 958

Text #12

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3314. Min Act: -0.0000

Data Index: 492049 (The Pile)

Max Activating Token Index: 966

Text #13

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3499. Min Act: -0.0000

Data Index: 354589 (The Pile)

Max Activating Token Index: 556

Text #14

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3225. Min Act: -0.0000

Data Index: 1705177 (The Pile)

Max Activating Token Index: 790

Text #15

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3159. Min Act: -0.0000

Data Index: 1569168 (The Pile)

Max Activating Token Index: 510

Text #16

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3231. Min Act: -0.0000

Data Index: 586554 (The Pile)

Max Activating Token Index: 868

Text #17

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3216. Min Act: -0.0000

Data Index: 1426986 (The Pile)

Max Activating Token Index: 271

Text #18

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3167. Min Act: -0.0000

Data Index: 1646856 (The Pile)

Max Activating Token Index: 892

Text #19

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3285. Min Act: -0.0000

Data Index: 171919 (The Pile)

Max Activating Token Index: 593