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

Dataset: The Pile

Neuron 3855 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: 1.7120. Min Range: -1.7120

Max Act: 1.7120. Min Act: -0.0000

Data Index: 517414 (The Pile)

Max Activating Token Index: 376

Text #1

Max Range: 1.7120. Min Range: -1.7120

Max Act: 1.6238. Min Act: -0.0000

Data Index: 1977847 (The Pile)

Max Activating Token Index: 169

Text #2

Max Range: 1.7120. Min Range: -1.7120

Max Act: 1.5224. Min Act: -0.0000

Data Index: 1483498 (The Pile)

Max Activating Token Index: 803

Text #3

Max Range: 1.7120. Min Range: -1.7120

Max Act: 1.2792. Min Act: -0.0000

Data Index: 1707480 (The Pile)

Max Activating Token Index: 181

Text #4

Max Range: 1.7120. Min Range: -1.7120

Max Act: 1.3546. Min Act: -0.0000

Data Index: 382586 (The Pile)

Max Activating Token Index: 1011

Text #5

Max Range: 1.7120. Min Range: -1.7120

Max Act: 1.1687. Min Act: -0.0000

Data Index: 1806613 (The Pile)

Max Activating Token Index: 328

Text #6

Max Range: 1.7120. Min Range: -1.7120

Max Act: 1.0987. Min Act: -0.0000

Data Index: 116587 (The Pile)

Max Activating Token Index: 711

Text #7

Max Range: 1.7120. Min Range: -1.7120

Max Act: 0.9890. Min Act: -0.0000

Data Index: 361366 (The Pile)

Max Activating Token Index: 61

Text #8

Max Range: 1.7120. Min Range: -1.7120

Max Act: 1.2789. Min Act: -0.0000

Data Index: 1809540 (The Pile)

Max Activating Token Index: 605

Text #9

Max Range: 1.7120. Min Range: -1.7120

Max Act: 1.1489. Min Act: -0.0000

Data Index: 1717907 (The Pile)

Max Activating Token Index: 516

Text #10

Max Range: 1.7120. Min Range: -1.7120

Max Act: 1.0954. Min Act: -0.0000

Data Index: 1175959 (The Pile)

Max Activating Token Index: 95

Text #11

Max Range: 1.7120. Min Range: -1.7120

Max Act: 1.1704. Min Act: -0.0000

Data Index: 936569 (The Pile)

Max Activating Token Index: 388

Text #12

Max Range: 1.7120. Min Range: -1.7120

Max Act: 1.0815. Min Act: -0.0000

Data Index: 1223747 (The Pile)

Max Activating Token Index: 926

Text #13

Max Range: 1.7120. Min Range: -1.7120

Max Act: 1.0977. Min Act: -0.0000

Data Index: 197556 (The Pile)

Max Activating Token Index: 973

Text #14

Max Range: 1.7120. Min Range: -1.7120

Max Act: 1.1051. Min Act: -0.0000

Data Index: 198095 (The Pile)

Max Activating Token Index: 83

Text #15

Max Range: 1.7120. Min Range: -1.7120

Max Act: 1.0409. Min Act: -0.0000

Data Index: 1200489 (The Pile)

Max Activating Token Index: 125

Text #16

Max Range: 1.7120. Min Range: -1.7120

Max Act: 1.0951. Min Act: -0.0000

Data Index: 833170 (The Pile)

Max Activating Token Index: 291

Text #17

Max Range: 1.7120. Min Range: -1.7120

Max Act: 1.0059. Min Act: -0.0000

Data Index: 543730 (The Pile)

Max Activating Token Index: 171

Text #18

Max Range: 1.7120. Min Range: -1.7120

Max Act: 0.9784. Min Act: -0.0000

Data Index: 1458350 (The Pile)

Max Activating Token Index: 870

Text #19

Max Range: 1.7120. Min Range: -1.7120

Max Act: 1.0945. Min Act: -0.0000

Data Index: 1022711 (The Pile)

Max Activating Token Index: 58