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

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

Neuron 3557 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1251. Min Range: -4.1251

Max Act: 4.1251. Min Act: -0.0000

Data Index: 193122 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 4.1251. Min Range: -4.1251

Max Act: 3.3932. Min Act: -0.0000

Data Index: 1133976 (C4 (Web Text))

Max Activating Token Index: 644

Text #2

Max Range: 4.1251. Min Range: -4.1251

Max Act: 3.1504. Min Act: -0.0000

Data Index: 319884 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 4.1251. Min Range: -4.1251

Max Act: 3.1406. Min Act: -0.0000

Data Index: 1240887 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 4.1251. Min Range: -4.1251

Max Act: 3.0773. Min Act: -0.0000

Data Index: 1182851 (C4 (Web Text))

Max Activating Token Index: 616

Text #5

Max Range: 4.1251. Min Range: -4.1251

Max Act: 3.0698. Min Act: -0.0000

Data Index: 432546 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 4.1251. Min Range: -4.1251

Max Act: 3.0501. Min Act: -0.0000

Data Index: 145396 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 4.1251. Min Range: -4.1251

Max Act: 3.0451. Min Act: -0.0000

Data Index: 89363 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 4.1251. Min Range: -4.1251

Max Act: 2.9923. Min Act: -0.0000

Data Index: 1168960 (C4 (Web Text))

Max Activating Token Index: 623

Text #9

Max Range: 4.1251. Min Range: -4.1251

Max Act: 2.9471. Min Act: -0.0000

Data Index: 156550 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 4.1251. Min Range: -4.1251

Max Act: 2.8794. Min Act: -0.0000

Data Index: 957067 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 4.1251. Min Range: -4.1251

Max Act: 2.8347. Min Act: 0.0000

Data Index: 497852 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 4.1251. Min Range: -4.1251

Max Act: 2.6906. Min Act: -0.0000

Data Index: 1184821 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 4.1251. Min Range: -4.1251

Max Act: 2.8036. Min Act: -0.0000

Data Index: 607354 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 4.1251. Min Range: -4.1251

Max Act: 2.6573. Min Act: -0.0000

Data Index: 642491 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 4.1251. Min Range: -4.1251

Max Act: 2.7741. Min Act: -0.0000

Data Index: 1168973 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 4.1251. Min Range: -4.1251

Max Act: 2.7963. Min Act: 0.0000

Data Index: 602249 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 4.1251. Min Range: -4.1251

Max Act: 2.7477. Min Act: -0.0000

Data Index: 986394 (C4 (Web Text))

Max Activating Token Index: 667

Text #18

Max Range: 4.1251. Min Range: -4.1251

Max Act: 2.5434. Min Act: -0.0000

Data Index: 605263 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 4.1251. Min Range: -4.1251

Max Act: 2.7899. Min Act: -0.0000

Data Index: 747710 (C4 (Web Text))

Max Activating Token Index: 513