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

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

Neuron 1046 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: 0.5072. Min Range: -0.5072

Max Act: 0.5062. Min Act: -0.0000

Data Index: 120024 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.5072. Min Act: -0.0000

Data Index: 345541 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4815. Min Act: -0.0000

Data Index: 771606 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4787. Min Act: -0.0000

Data Index: 1208572 (C4 (Web Text))

Max Activating Token Index: 398

Text #4

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4701. Min Act: -0.0000

Data Index: 60114 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4494. Min Act: -0.0000

Data Index: 610769 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4481. Min Act: -0.0000

Data Index: 1200007 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4776. Min Act: -0.0000

Data Index: 1068264 (C4 (Web Text))

Max Activating Token Index: 481

Text #8

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4515. Min Act: -0.0000

Data Index: 759914 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4698. Min Act: -0.0000

Data Index: 737060 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4447. Min Act: -0.0000

Data Index: 173115 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4090. Min Act: -0.0000

Data Index: 618057 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4240. Min Act: -0.0000

Data Index: 41317 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4238. Min Act: -0.0000

Data Index: 824046 (C4 (Web Text))

Max Activating Token Index: 798

Text #14

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4360. Min Act: -0.0000

Data Index: 554708 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4222. Min Act: -0.0000

Data Index: 64983 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3977. Min Act: -0.0000

Data Index: 894098 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4293. Min Act: -0.0000

Data Index: 84464 (C4 (Web Text))

Max Activating Token Index: 572

Text #18

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4021. Min Act: -0.0000

Data Index: 730052 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3958. Min Act: -0.0000

Data Index: 1162554 (C4 (Web Text))

Max Activating Token Index: 325