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

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

Neuron 473 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.5071. Min Act: -0.0000

Data Index: 274187 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.4833. Min Act: -0.0000

Data Index: 482744 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.4813. Min Act: -0.0000

Data Index: 1044366 (C4 (Web Text))

Max Activating Token Index: 938

Text #3

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.4596. Min Act: -0.0000

Data Index: 397055 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.4319. Min Act: -0.0000

Data Index: 759150 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.4386. Min Act: -0.0000

Data Index: 1118334 (C4 (Web Text))

Max Activating Token Index: 485

Text #6

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.4025. Min Act: -0.0000

Data Index: 26052 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.4122. Min Act: -0.0000

Data Index: 100565 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.3871. Min Act: -0.0000

Data Index: 458528 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.3715. Min Act: -0.0000

Data Index: 208004 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.3846. Min Act: -0.0000

Data Index: 24039 (C4 (Web Text))

Max Activating Token Index: 593

Text #11

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.3499. Min Act: -0.0000

Data Index: 82358 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.3818. Min Act: -0.0000

Data Index: 218669 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.3556. Min Act: -0.0000

Data Index: 1298066 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.3673. Min Act: -0.0000

Data Index: 517982 (C4 (Web Text))

Max Activating Token Index: 810

Text #15

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.3643. Min Act: -0.0000

Data Index: 240448 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.3738. Min Act: -0.0000

Data Index: 1166213 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.3606. Min Act: -0.0000

Data Index: 1011487 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.3570. Min Act: -0.0000

Data Index: 1274833 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.3794. Min Act: -0.0000

Data Index: 89010 (C4 (Web Text))

Max Activating Token Index: 698