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

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

Neuron 2648 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9375. Min Range: -0.9375

Max Act: 0.9375. Min Act: -0.0000

Data Index: 533061 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 0.9375. Min Range: -0.9375

Max Act: 0.9095. Min Act: -0.0000

Data Index: 1141557 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 0.9375. Min Range: -0.9375

Max Act: 0.8184. Min Act: -0.0000

Data Index: 535095 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 0.9375. Min Range: -0.9375

Max Act: 0.8100. Min Act: -0.0000

Data Index: 913946 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 0.9375. Min Range: -0.9375

Max Act: 0.6622. Min Act: -0.0000

Data Index: 178787 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 0.9375. Min Range: -0.9375

Max Act: 0.6616. Min Act: -0.0000

Data Index: 116733 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 0.9375. Min Range: -0.9375

Max Act: 0.6453. Min Act: -0.0000

Data Index: 1125995 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 0.9375. Min Range: -0.9375

Max Act: 0.6012. Min Act: -0.0000

Data Index: 967205 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 0.9375. Min Range: -0.9375

Max Act: 0.6000. Min Act: -0.0000

Data Index: 596517 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 0.9375. Min Range: -0.9375

Max Act: 0.5895. Min Act: -0.0000

Data Index: 28776 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 0.9375. Min Range: -0.9375

Max Act: 0.6016. Min Act: -0.0000

Data Index: 322427 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 0.9375. Min Range: -0.9375

Max Act: 0.5559. Min Act: -0.0000

Data Index: 573915 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 0.9375. Min Range: -0.9375

Max Act: 0.5984. Min Act: -0.0000

Data Index: 345161 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 0.9375. Min Range: -0.9375

Max Act: 0.5918. Min Act: -0.0000

Data Index: 406872 (C4 (Web Text))

Max Activating Token Index: 560

Text #14

Max Range: 0.9375. Min Range: -0.9375

Max Act: 0.5787. Min Act: -0.0000

Data Index: 474757 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 0.9375. Min Range: -0.9375

Max Act: 0.5709. Min Act: -0.0000

Data Index: 486913 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 0.9375. Min Range: -0.9375

Max Act: 0.5793. Min Act: -0.0000

Data Index: 1374703 (Python Code)

Max Activating Token Index: 567

Text #17

Max Range: 0.9375. Min Range: -0.9375

Max Act: 0.5189. Min Act: -0.0000

Data Index: 120408 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 0.9375. Min Range: -0.9375

Max Act: 0.5060. Min Act: -0.0000

Data Index: 961614 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 0.9375. Min Range: -0.9375

Max Act: 0.5727. Min Act: -0.0000

Data Index: 1531620 (Python Code)

Max Activating Token Index: 295