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

Dataset: The Pile

Neuron 3967 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: 3.3817. Min Range: -3.3817

Max Act: 3.3817. Min Act: -0.0000

Data Index: 1144261 (The Pile)

Max Activating Token Index: 545

Text #1

Max Range: 3.3817. Min Range: -3.3817

Max Act: 3.1601. Min Act: -0.0000

Data Index: 1963439 (The Pile)

Max Activating Token Index: 999

Text #2

Max Range: 3.3817. Min Range: -3.3817

Max Act: 2.9693. Min Act: -0.0000

Data Index: 1398484 (The Pile)

Max Activating Token Index: 491

Text #3

Max Range: 3.3817. Min Range: -3.3817

Max Act: 2.7594. Min Act: -0.0000

Data Index: 1168954 (The Pile)

Max Activating Token Index: 144

Text #4

Max Range: 3.3817. Min Range: -3.3817

Max Act: 2.7526. Min Act: -0.0000

Data Index: 1325356 (The Pile)

Max Activating Token Index: 523

Text #5

Max Range: 3.3817. Min Range: -3.3817

Max Act: 2.7191. Min Act: -0.0000

Data Index: 323660 (The Pile)

Max Activating Token Index: 34

Text #6

Max Range: 3.3817. Min Range: -3.3817

Max Act: 2.8279. Min Act: -0.0000

Data Index: 424248 (The Pile)

Max Activating Token Index: 184

Text #7

Max Range: 3.3817. Min Range: -3.3817

Max Act: 2.5812. Min Act: -0.0000

Data Index: 935778 (The Pile)

Max Activating Token Index: 592

Text #8

Max Range: 3.3817. Min Range: -3.3817

Max Act: 2.6898. Min Act: -0.0000

Data Index: 1900357 (The Pile)

Max Activating Token Index: 277

Text #9

Max Range: 3.3817. Min Range: -3.3817

Max Act: 2.5193. Min Act: -0.0000

Data Index: 1605068 (The Pile)

Max Activating Token Index: 527

Text #10

Max Range: 3.3817. Min Range: -3.3817

Max Act: 2.4698. Min Act: -0.0000

Data Index: 1766610 (The Pile)

Max Activating Token Index: 732

Text #11

Max Range: 3.3817. Min Range: -3.3817

Max Act: 2.5686. Min Act: -0.0000

Data Index: 1125776 (The Pile)

Max Activating Token Index: 231

Text #12

Max Range: 3.3817. Min Range: -3.3817

Max Act: 2.5240. Min Act: -0.0000

Data Index: 1283396 (The Pile)

Max Activating Token Index: 156

Text #13

Max Range: 3.3817. Min Range: -3.3817

Max Act: 2.3013. Min Act: -0.0000

Data Index: 1822383 (The Pile)

Max Activating Token Index: 700

Text #14

Max Range: 3.3817. Min Range: -3.3817

Max Act: 1.9731. Min Act: -0.0000

Data Index: 1648616 (The Pile)

Max Activating Token Index: 830

Text #15

Max Range: 3.3817. Min Range: -3.3817

Max Act: 2.0028. Min Act: -0.0000

Data Index: 633416 (The Pile)

Max Activating Token Index: 721

Text #16

Max Range: 3.3817. Min Range: -3.3817

Max Act: 2.2045. Min Act: -0.0000

Data Index: 1861648 (The Pile)

Max Activating Token Index: 513

Text #17

Max Range: 3.3817. Min Range: -3.3817

Max Act: 2.5406. Min Act: -0.0000

Data Index: 1572309 (The Pile)

Max Activating Token Index: 337

Text #18

Max Range: 3.3817. Min Range: -3.3817

Max Act: 2.2573. Min Act: -0.0000

Data Index: 1509712 (The Pile)

Max Activating Token Index: 532

Text #19

Max Range: 3.3817. Min Range: -3.3817

Max Act: 2.2488. Min Act: -0.0000

Data Index: 478141 (The Pile)

Max Activating Token Index: 15