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

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

Neuron 3120 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: 0.0908. Min Range: -0.0908

Max Act: 0.0824. Min Act: -0.0000

Data Index: 428259 (C4 (Web Text))

Max Activating Token Index: 437

Text #1

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0847. Min Act: -0.0000

Data Index: 150357 (C4 (Web Text))

Max Activating Token Index: 495

Text #2

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0908. Min Act: -0.0000

Data Index: 825132 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0848. Min Act: 0.0001

Data Index: 614627 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0844. Min Act: -0.0000

Data Index: 1282085 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0816. Min Act: 0.0000

Data Index: 686515 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0738. Min Act: 0.0000

Data Index: 1096828 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0852. Min Act: 0.0001

Data Index: 951259 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0780. Min Act: 0.0001

Data Index: 606278 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0782. Min Act: -0.0000

Data Index: 1242903 (C4 (Web Text))

Max Activating Token Index: 534

Text #10

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0766. Min Act: -0.0000

Data Index: 150708 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0740. Min Act: -0.0000

Data Index: 1217838 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0753. Min Act: -0.0000

Data Index: 1300852 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0720. Min Act: -0.0000

Data Index: 109899 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0714. Min Act: -0.0000

Data Index: 1138642 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0714. Min Act: -0.0000

Data Index: 527833 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0730. Min Act: -0.0000

Data Index: 889286 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0731. Min Act: -0.0000

Data Index: 66027 (C4 (Web Text))

Max Activating Token Index: 457

Text #18

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0699. Min Act: -0.0000

Data Index: 572445 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0752. Min Act: -0.0000

Data Index: 814926 (C4 (Web Text))

Max Activating Token Index: 42