Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 256 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.9674. Min Act: -0.0000

Data Index: 471086 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.7298. Min Act: -0.0000

Data Index: 350651 (C4 (Web Text))

Max Activating Token Index: 689

Text #2

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.7035. Min Act: -0.0000

Data Index: 1058317 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.6650. Min Act: -0.0000

Data Index: 834636 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.6639. Min Act: -0.0000

Data Index: 829058 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.5977. Min Act: -0.0000

Data Index: 1126204 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.6247. Min Act: -0.0000

Data Index: 264058 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.6430. Min Act: -0.0000

Data Index: 1225839 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.6304. Min Act: -0.0000

Data Index: 933079 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.6012. Min Act: -0.0000

Data Index: 662328 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.5653. Min Act: -0.0000

Data Index: 614100 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.5564. Min Act: -0.0000

Data Index: 381834 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.5501. Min Act: -0.0000

Data Index: 1028506 (C4 (Web Text))

Max Activating Token Index: 406

Text #13

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.5641. Min Act: -0.0000

Data Index: 650767 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.5403. Min Act: 0.0001

Data Index: 613878 (C4 (Web Text))

Max Activating Token Index: 544

Text #15

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.5218. Min Act: -0.0000

Data Index: 186555 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.5002. Min Act: -0.0000

Data Index: 462511 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.5144. Min Act: -0.0000

Data Index: 1087972 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.5280. Min Act: -0.0000

Data Index: 961507 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.5235. Min Act: -0.0000

Data Index: 68439 (C4 (Web Text))

Max Activating Token Index: 192