Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2880 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.8971. Min Act: -0.0000

Data Index: 702171 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.9009. Min Act: 0.0001

Data Index: 846609 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.7899. Min Act: 0.0000

Data Index: 288728 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.8332. Min Act: 0.0001

Data Index: 306867 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.7820. Min Act: -0.0000

Data Index: 503717 (C4 (Web Text))

Max Activating Token Index: 724

Text #5

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.7220. Min Act: -0.0000

Data Index: 832630 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.6850. Min Act: -0.0000

Data Index: 1292478 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.6985. Min Act: -0.0000

Data Index: 792430 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.7308. Min Act: -0.0000

Data Index: 530031 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.6959. Min Act: 0.0000

Data Index: 168631 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.6630. Min Act: -0.0000

Data Index: 783498 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.7050. Min Act: -0.0000

Data Index: 246157 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.6544. Min Act: 0.0000

Data Index: 843473 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.6282. Min Act: 0.0001

Data Index: 1262947 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.6302. Min Act: 0.0000

Data Index: 307159 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.6715. Min Act: -0.0000

Data Index: 270975 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.6369. Min Act: -0.0000

Data Index: 1541970 (Python Code)

Max Activating Token Index: 593

Text #17

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.6258. Min Act: 0.0000

Data Index: 696052 (C4 (Web Text))

Max Activating Token Index: 714

Text #18

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.6426. Min Act: -0.0001

Data Index: 583513 (C4 (Web Text))

Max Activating Token Index: 474

Text #19

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.6196. Min Act: -0.0000

Data Index: 1162608 (C4 (Web Text))

Max Activating Token Index: 689