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

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

Neuron 3510 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.7580. Min Act: 0.0000

Data Index: 675901 (C4 (Web Text))

Max Activating Token Index: 767

Text #1

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.6604. Min Act: -0.0000

Data Index: 32565 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.6266. Min Act: -0.0000

Data Index: 534475 (C4 (Web Text))

Max Activating Token Index: 516

Text #3

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.6842. Min Act: -0.0000

Data Index: 721192 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.6564. Min Act: -0.0000

Data Index: 6729 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.5931. Min Act: -0.0000

Data Index: 930433 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.6618. Min Act: -0.0000

Data Index: 359646 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.6090. Min Act: 0.0000

Data Index: 1145287 (C4 (Web Text))

Max Activating Token Index: 568

Text #8

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.6376. Min Act: -0.0000

Data Index: 853117 (C4 (Web Text))

Max Activating Token Index: 380

Text #9

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.6375. Min Act: -0.0000

Data Index: 1122606 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.5912. Min Act: -0.0000

Data Index: 215071 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.6279. Min Act: -0.0000

Data Index: 344391 (C4 (Web Text))

Max Activating Token Index: 394

Text #12

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.6014. Min Act: -0.0000

Data Index: 897822 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.5665. Min Act: -0.0000

Data Index: 998444 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.6188. Min Act: -0.0000

Data Index: 623137 (C4 (Web Text))

Max Activating Token Index: 237

Text #15

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.5910. Min Act: -0.0000

Data Index: 847940 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.6158. Min Act: -0.0000

Data Index: 341444 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.5921. Min Act: 0.0000

Data Index: 380569 (C4 (Web Text))

Max Activating Token Index: 605

Text #18

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.5558. Min Act: -0.0000

Data Index: 468774 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.5586. Min Act: -0.0000

Data Index: 684653 (C4 (Web Text))

Max Activating Token Index: 468