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

Dataset: The Pile

Neuron 2609 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: 0.5591. Min Range: -0.5591

Max Act: 0.5591. Min Act: -0.0001

Data Index: 1270590 (The Pile)

Max Activating Token Index: 917

Text #1

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.5332. Min Act: -0.0000

Data Index: 832895 (The Pile)

Max Activating Token Index: 545

Text #2

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.5441. Min Act: -0.0000

Data Index: 211890 (The Pile)

Max Activating Token Index: 369

Text #3

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4859. Min Act: -0.0000

Data Index: 1911347 (The Pile)

Max Activating Token Index: 803

Text #4

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4590. Min Act: -0.0000

Data Index: 1834113 (The Pile)

Max Activating Token Index: 504

Text #5

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4406. Min Act: -0.0000

Data Index: 1661617 (The Pile)

Max Activating Token Index: 516

Text #6

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4640. Min Act: -0.0000

Data Index: 1393269 (The Pile)

Max Activating Token Index: 394

Text #7

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4430. Min Act: -0.0000

Data Index: 1837036 (The Pile)

Max Activating Token Index: 512

Text #8

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4921. Min Act: -0.0000

Data Index: 715815 (The Pile)

Max Activating Token Index: 772

Text #9

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4207. Min Act: -0.0000

Data Index: 981172 (The Pile)

Max Activating Token Index: 679

Text #10

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4563. Min Act: -0.0000

Data Index: 1369196 (The Pile)

Max Activating Token Index: 607

Text #11

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4172. Min Act: -0.0000

Data Index: 344912 (The Pile)

Max Activating Token Index: 472

Text #12

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4292. Min Act: -0.0000

Data Index: 1257374 (The Pile)

Max Activating Token Index: 768

Text #13

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4295. Min Act: -0.0000

Data Index: 1647743 (The Pile)

Max Activating Token Index: 780

Text #14

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4308. Min Act: -0.0000

Data Index: 441299 (The Pile)

Max Activating Token Index: 496

Text #15

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4514. Min Act: -0.0000

Data Index: 1931530 (The Pile)

Max Activating Token Index: 571

Text #16

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4238. Min Act: -0.0000

Data Index: 1103855 (The Pile)

Max Activating Token Index: 246

Text #17

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4055. Min Act: -0.0000

Data Index: 1482440 (The Pile)

Max Activating Token Index: 813

Text #18

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.3897. Min Act: -0.0000

Data Index: 480453 (The Pile)

Max Activating Token Index: 488

Text #19

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.3944. Min Act: -0.0000

Data Index: 1558753 (The Pile)

Max Activating Token Index: 228