Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 650 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0918. Min Act: -0.0003

Data Index: 896526 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0855. Min Act: -0.0003

Data Index: 278662 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0760. Min Act: -0.0003

Data Index: 414486 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0691. Min Act: -0.0003

Data Index: 243323 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0712. Min Act: -0.0003

Data Index: 1098517 (C4 (Web Text))

Max Activating Token Index: 708

Text #5

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0774. Min Act: -0.0003

Data Index: 592014 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0771. Min Act: -0.0003

Data Index: 1279332 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0716. Min Act: -0.0003

Data Index: 423260 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0741. Min Act: -0.0003

Data Index: 1054162 (C4 (Web Text))

Max Activating Token Index: 224

Text #9

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0733. Min Act: -0.0003

Data Index: 89114 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0802. Min Act: -0.0003

Data Index: 447199 (C4 (Web Text))

Max Activating Token Index: 673

Text #11

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0766. Min Act: -0.0003

Data Index: 1146006 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0719. Min Act: -0.0003

Data Index: 1019009 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0731. Min Act: -0.0003

Data Index: 356125 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0748. Min Act: -0.0003

Data Index: 596621 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0685. Min Act: -0.0003

Data Index: 444872 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0705. Min Act: -0.0003

Data Index: 1042982 (C4 (Web Text))

Max Activating Token Index: 772

Text #17

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0662. Min Act: -0.0003

Data Index: 715794 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0674. Min Act: -0.0003

Data Index: 77511 (C4 (Web Text))

Max Activating Token Index: 972

Text #19

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0693. Min Act: -0.0003

Data Index: 1127410 (C4 (Web Text))

Max Activating Token Index: 154