Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3817 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0889. Min Act: -0.0002

Data Index: 1201923 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0919. Min Act: -0.0002

Data Index: 344761 (C4 (Web Text))

Max Activating Token Index: 532

Text #2

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0896. Min Act: -0.0002

Data Index: 676273 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0857. Min Act: -0.0002

Data Index: 279847 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0818. Min Act: -0.0002

Data Index: 303186 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0836. Min Act: -0.0002

Data Index: 174353 (C4 (Web Text))

Max Activating Token Index: 715

Text #6

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0797. Min Act: -0.0002

Data Index: 1230485 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0821. Min Act: -0.0002

Data Index: 568308 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0828. Min Act: -0.0002

Data Index: 16329 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0796. Min Act: -0.0002

Data Index: 760572 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0795. Min Act: -0.0002

Data Index: 1054160 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0741. Min Act: -0.0002

Data Index: 1344738 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0761. Min Act: -0.0002

Data Index: 1062594 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0755. Min Act: -0.0002

Data Index: 168302 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0753. Min Act: -0.0002

Data Index: 415585 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0703. Min Act: -0.0002

Data Index: 542386 (C4 (Web Text))

Max Activating Token Index: 513

Text #16

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0755. Min Act: -0.0002

Data Index: 194304 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0725. Min Act: -0.0002

Data Index: 85494 (C4 (Web Text))

Max Activating Token Index: 478

Text #18

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0711. Min Act: -0.0002

Data Index: 233888 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0748. Min Act: -0.0002

Data Index: 167328 (C4 (Web Text))

Max Activating Token Index: 756