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

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

Neuron 1838 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4329. Min Range: -3.4329

Max Act: 3.4329. Min Act: -0.0000

Data Index: 1044393 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 3.4329. Min Range: -3.4329

Max Act: 2.9732. Min Act: -0.0000

Data Index: 840991 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 3.4329. Min Range: -3.4329

Max Act: 3.0615. Min Act: -0.0000

Data Index: 729413 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 3.4329. Min Range: -3.4329

Max Act: 2.6140. Min Act: -0.0000

Data Index: 187505 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 3.4329. Min Range: -3.4329

Max Act: 2.8687. Min Act: -0.0000

Data Index: 598648 (C4 (Web Text))

Max Activating Token Index: 387

Text #5

Max Range: 3.4329. Min Range: -3.4329

Max Act: 2.9719. Min Act: -0.0000

Data Index: 239845 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 3.4329. Min Range: -3.4329

Max Act: 2.6404. Min Act: -0.0000

Data Index: 294253 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 3.4329. Min Range: -3.4329

Max Act: 2.9298. Min Act: -0.0000

Data Index: 965790 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 3.4329. Min Range: -3.4329

Max Act: 2.9047. Min Act: -0.0000

Data Index: 997903 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 3.4329. Min Range: -3.4329

Max Act: 2.6977. Min Act: -0.0000

Data Index: 983188 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 3.4329. Min Range: -3.4329

Max Act: 2.7163. Min Act: -0.0000

Data Index: 31631 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 3.4329. Min Range: -3.4329

Max Act: 2.6726. Min Act: -0.0000

Data Index: 925742 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 3.4329. Min Range: -3.4329

Max Act: 2.5709. Min Act: -0.0000

Data Index: 178600 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 3.4329. Min Range: -3.4329

Max Act: 2.6977. Min Act: -0.0000

Data Index: 45242 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 3.4329. Min Range: -3.4329

Max Act: 2.5278. Min Act: -0.0000

Data Index: 125548 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 3.4329. Min Range: -3.4329

Max Act: 2.4930. Min Act: -0.0000

Data Index: 577456 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 3.4329. Min Range: -3.4329

Max Act: 2.7098. Min Act: -0.0000

Data Index: 960499 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 3.4329. Min Range: -3.4329

Max Act: 2.4038. Min Act: -0.0000

Data Index: 584564 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 3.4329. Min Range: -3.4329

Max Act: 2.3670. Min Act: -0.0000

Data Index: 511453 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 3.4329. Min Range: -3.4329

Max Act: 2.5240. Min Act: -0.0000

Data Index: 1134276 (C4 (Web Text))

Max Activating Token Index: 586