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

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

Neuron 668 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0819. Min Range: -2.0819

Max Act: 2.0819. Min Act: -0.0000

Data Index: 855522 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 2.0819. Min Range: -2.0819

Max Act: 1.9322. Min Act: -0.0000

Data Index: 454083 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 2.0819. Min Range: -2.0819

Max Act: 1.7883. Min Act: -0.0000

Data Index: 1145181 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 2.0819. Min Range: -2.0819

Max Act: 1.7391. Min Act: -0.0000

Data Index: 198367 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 2.0819. Min Range: -2.0819

Max Act: 1.8742. Min Act: -0.0000

Data Index: 1083439 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 2.0819. Min Range: -2.0819

Max Act: 1.7371. Min Act: -0.0000

Data Index: 457151 (C4 (Web Text))

Max Activating Token Index: 864

Text #6

Max Range: 2.0819. Min Range: -2.0819

Max Act: 1.5197. Min Act: -0.0000

Data Index: 352315 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 2.0819. Min Range: -2.0819

Max Act: 1.6218. Min Act: -0.0000

Data Index: 581693 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 2.0819. Min Range: -2.0819

Max Act: 1.5308. Min Act: -0.0000

Data Index: 222647 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 2.0819. Min Range: -2.0819

Max Act: 1.6897. Min Act: -0.0000

Data Index: 947434 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 2.0819. Min Range: -2.0819

Max Act: 1.7543. Min Act: -0.0000

Data Index: 366576 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 2.0819. Min Range: -2.0819

Max Act: 1.4404. Min Act: -0.0000

Data Index: 178450 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 2.0819. Min Range: -2.0819

Max Act: 1.4551. Min Act: -0.0000

Data Index: 338967 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 2.0819. Min Range: -2.0819

Max Act: 1.5065. Min Act: -0.0000

Data Index: 810168 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 2.0819. Min Range: -2.0819

Max Act: 1.4015. Min Act: -0.0000

Data Index: 597220 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 2.0819. Min Range: -2.0819

Max Act: 1.4095. Min Act: -0.0000

Data Index: 1173538 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 2.0819. Min Range: -2.0819

Max Act: 1.5544. Min Act: -0.0000

Data Index: 554917 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 2.0819. Min Range: -2.0819

Max Act: 1.4710. Min Act: -0.0000

Data Index: 565890 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 2.0819. Min Range: -2.0819

Max Act: 1.4611. Min Act: -0.0000

Data Index: 665256 (C4 (Web Text))

Max Activating Token Index: 468

Text #19

Max Range: 2.0819. Min Range: -2.0819

Max Act: 1.4590. Min Act: -0.0000

Data Index: 161825 (C4 (Web Text))

Max Activating Token Index: 48