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

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

Neuron 2393 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: 2.2678. Min Range: -2.2678

Max Act: 2.2678. Min Act: -0.0000

Data Index: 318511 (C4 (Web Text))

Max Activating Token Index: 779

Text #1

Max Range: 2.2678. Min Range: -2.2678

Max Act: 1.8568. Min Act: -0.0000

Data Index: 83151 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 2.2678. Min Range: -2.2678

Max Act: 1.8088. Min Act: -0.0000

Data Index: 1045653 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 2.2678. Min Range: -2.2678

Max Act: 1.7744. Min Act: -0.0000

Data Index: 328781 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 2.2678. Min Range: -2.2678

Max Act: 1.5959. Min Act: -0.0000

Data Index: 269666 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 2.2678. Min Range: -2.2678

Max Act: 1.4571. Min Act: -0.0000

Data Index: 442949 (C4 (Web Text))

Max Activating Token Index: 931

Text #6

Max Range: 2.2678. Min Range: -2.2678

Max Act: 1.6018. Min Act: -0.0000

Data Index: 659007 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 2.2678. Min Range: -2.2678

Max Act: 1.6031. Min Act: -0.0000

Data Index: 721089 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 2.2678. Min Range: -2.2678

Max Act: 1.5868. Min Act: -0.0000

Data Index: 1201449 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 2.2678. Min Range: -2.2678

Max Act: 1.4391. Min Act: -0.0000

Data Index: 165318 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 2.2678. Min Range: -2.2678

Max Act: 1.5355. Min Act: -0.0000

Data Index: 1233350 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 2.2678. Min Range: -2.2678

Max Act: 1.4275. Min Act: -0.0000

Data Index: 154434 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 2.2678. Min Range: -2.2678

Max Act: 1.5178. Min Act: -0.0000

Data Index: 769585 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 2.2678. Min Range: -2.2678

Max Act: 1.4072. Min Act: -0.0000

Data Index: 1289842 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 2.2678. Min Range: -2.2678

Max Act: 1.5036. Min Act: -0.0000

Data Index: 710792 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 2.2678. Min Range: -2.2678

Max Act: 1.4676. Min Act: -0.0000

Data Index: 254697 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 2.2678. Min Range: -2.2678

Max Act: 1.3724. Min Act: -0.0000

Data Index: 439810 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 2.2678. Min Range: -2.2678

Max Act: 1.3558. Min Act: -0.0000

Data Index: 99674 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 2.2678. Min Range: -2.2678

Max Act: 1.4161. Min Act: -0.0000

Data Index: 908287 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 2.2678. Min Range: -2.2678

Max Act: 1.2506. Min Act: -0.0000

Data Index: 1291323 (C4 (Web Text))

Max Activating Token Index: 825