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

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

Neuron 3479 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: 0.9504. Min Range: -0.9504

Max Act: 0.9504. Min Act: -0.0000

Data Index: 28777 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.7994. Min Act: -0.0000

Data Index: 1044279 (C4 (Web Text))

Max Activating Token Index: 369

Text #2

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.8003. Min Act: -0.0000

Data Index: 311589 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.7756. Min Act: -0.0000

Data Index: 499150 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.6906. Min Act: 0.0000

Data Index: 376664 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.7127. Min Act: 0.0000

Data Index: 598041 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.6564. Min Act: -0.0000

Data Index: 522985 (C4 (Web Text))

Max Activating Token Index: 558

Text #7

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.6274. Min Act: -0.0000

Data Index: 392610 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.5868. Min Act: -0.0000

Data Index: 535806 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.6711. Min Act: 0.0000

Data Index: 752683 (C4 (Web Text))

Max Activating Token Index: 995

Text #10

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.6011. Min Act: 0.0000

Data Index: 1207713 (C4 (Web Text))

Max Activating Token Index: 991

Text #11

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.6156. Min Act: -0.0000

Data Index: 501807 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.6287. Min Act: -0.0000

Data Index: 963532 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.6054. Min Act: 0.0000

Data Index: 559967 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.6058. Min Act: 0.0000

Data Index: 530229 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.5700. Min Act: -0.0000

Data Index: 120423 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.5957. Min Act: 0.0000

Data Index: 1205880 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.5817. Min Act: -0.0000

Data Index: 859018 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.5932. Min Act: -0.0000

Data Index: 974505 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.6483. Min Act: 0.0000

Data Index: 887793 (C4 (Web Text))

Max Activating Token Index: 707