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

Dataset: The Pile

Neuron 1894 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3966. Min Range: -1.3966

Max Act: 1.3101. Min Act: -0.0000

Data Index: 150865 (The Pile)

Max Activating Token Index: 236

Text #1

Max Range: 1.3966. Min Range: -1.3966

Max Act: 1.3966. Min Act: -0.0000

Data Index: 489914 (The Pile)

Max Activating Token Index: 218

Text #2

Max Range: 1.3966. Min Range: -1.3966

Max Act: 1.1702. Min Act: -0.0000

Data Index: 804900 (The Pile)

Max Activating Token Index: 122

Text #3

Max Range: 1.3966. Min Range: -1.3966

Max Act: 1.2733. Min Act: -0.0000

Data Index: 793928 (The Pile)

Max Activating Token Index: 289

Text #4

Max Range: 1.3966. Min Range: -1.3966

Max Act: 1.1878. Min Act: -0.0000

Data Index: 610593 (The Pile)

Max Activating Token Index: 461

Text #5

Max Range: 1.3966. Min Range: -1.3966

Max Act: 1.0879. Min Act: -0.0000

Data Index: 1960236 (The Pile)

Max Activating Token Index: 176

Text #6

Max Range: 1.3966. Min Range: -1.3966

Max Act: 1.0815. Min Act: -0.0000

Data Index: 905794 (The Pile)

Max Activating Token Index: 632

Text #7

Max Range: 1.3966. Min Range: -1.3966

Max Act: 1.1626. Min Act: -0.0000

Data Index: 1832076 (The Pile)

Max Activating Token Index: 143

Text #8

Max Range: 1.3966. Min Range: -1.3966

Max Act: 1.0731. Min Act: -0.0000

Data Index: 310065 (The Pile)

Max Activating Token Index: 86

Text #9

Max Range: 1.3966. Min Range: -1.3966

Max Act: 0.9683. Min Act: -0.0000

Data Index: 949314 (The Pile)

Max Activating Token Index: 442

Text #10

Max Range: 1.3966. Min Range: -1.3966

Max Act: 0.8406. Min Act: -0.0000

Data Index: 1977137 (The Pile)

Max Activating Token Index: 664

Text #11

Max Range: 1.3966. Min Range: -1.3966

Max Act: 0.8465. Min Act: -0.0000

Data Index: 1502943 (The Pile)

Max Activating Token Index: 516

Text #12

Max Range: 1.3966. Min Range: -1.3966

Max Act: 0.9553. Min Act: -0.0000

Data Index: 140797 (The Pile)

Max Activating Token Index: 244

Text #13

Max Range: 1.3966. Min Range: -1.3966

Max Act: 0.8489. Min Act: -0.0000

Data Index: 1999239 (The Pile)

Max Activating Token Index: 401

Text #14

Max Range: 1.3966. Min Range: -1.3966

Max Act: 0.8264. Min Act: -0.0000

Data Index: 1813020 (The Pile)

Max Activating Token Index: 583

Text #15

Max Range: 1.3966. Min Range: -1.3966

Max Act: 0.8035. Min Act: -0.0000

Data Index: 470235 (The Pile)

Max Activating Token Index: 246

Text #16

Max Range: 1.3966. Min Range: -1.3966

Max Act: 0.8778. Min Act: -0.0000

Data Index: 1722705 (The Pile)

Max Activating Token Index: 860

Text #17

Max Range: 1.3966. Min Range: -1.3966

Max Act: 0.6608. Min Act: -0.0000

Data Index: 36080 (The Pile)

Max Activating Token Index: 347

Text #18

Max Range: 1.3966. Min Range: -1.3966

Max Act: 0.9239. Min Act: -0.0000

Data Index: 76178 (The Pile)

Max Activating Token Index: 560

Text #19

Max Range: 1.3966. Min Range: -1.3966

Max Act: 0.7226. Min Act: -0.0000

Data Index: 1744346 (The Pile)

Max Activating Token Index: 33