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

Dataset: The Pile

Neuron 4864 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.9369. Min Act: -0.0000

Data Index: 160815 (The Pile)

Max Activating Token Index: 332

Text #1

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.8882. Min Act: -0.0000

Data Index: 530148 (The Pile)

Max Activating Token Index: 30

Text #2

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.7733. Min Act: -0.0000

Data Index: 926497 (The Pile)

Max Activating Token Index: 571

Text #3

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.7119. Min Act: -0.0000

Data Index: 511558 (The Pile)

Max Activating Token Index: 539

Text #4

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.6608. Min Act: -0.0000

Data Index: 1619720 (The Pile)

Max Activating Token Index: 700

Text #5

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.6131. Min Act: -0.0000

Data Index: 1452650 (The Pile)

Max Activating Token Index: 250

Text #6

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.6255. Min Act: -0.0000

Data Index: 798335 (The Pile)

Max Activating Token Index: 639

Text #7

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.5685. Min Act: -0.0000

Data Index: 886750 (The Pile)

Max Activating Token Index: 240

Text #8

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.5470. Min Act: -0.0000

Data Index: 1029282 (The Pile)

Max Activating Token Index: 941

Text #9

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.5196. Min Act: -0.0000

Data Index: 525425 (The Pile)

Max Activating Token Index: 779

Text #10

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.5505. Min Act: -0.0000

Data Index: 1916648 (The Pile)

Max Activating Token Index: 506

Text #11

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.5512. Min Act: -0.0000

Data Index: 1942874 (The Pile)

Max Activating Token Index: 856

Text #12

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.5297. Min Act: -0.0000

Data Index: 646013 (The Pile)

Max Activating Token Index: 32

Text #13

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.4842. Min Act: -0.0000

Data Index: 1125747 (The Pile)

Max Activating Token Index: 883

Text #14

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.5038. Min Act: -0.0000

Data Index: 1336073 (The Pile)

Max Activating Token Index: 165

Text #15

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.4855. Min Act: -0.0000

Data Index: 87061 (The Pile)

Max Activating Token Index: 325

Text #16

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.5195. Min Act: -0.0000

Data Index: 1696906 (The Pile)

Max Activating Token Index: 101

Text #17

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.5006. Min Act: -0.0000

Data Index: 1188436 (The Pile)

Max Activating Token Index: 564

Text #18

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.4802. Min Act: -0.0000

Data Index: 49180 (The Pile)

Max Activating Token Index: 43

Text #19

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.4647. Min Act: -0.0000

Data Index: 519420 (The Pile)

Max Activating Token Index: 17