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

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

Neuron 4712 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0853. Min Act: -0.0002

Data Index: 915205 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0882. Min Act: -0.0003

Data Index: 99091 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0850. Min Act: -0.0003

Data Index: 39547 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0837. Min Act: -0.0003

Data Index: 301499 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0780. Min Act: -0.0002

Data Index: 968110 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0878. Min Act: -0.0002

Data Index: 876230 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0808. Min Act: -0.0003

Data Index: 877983 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0769. Min Act: -0.0002

Data Index: 620137 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0739. Min Act: -0.0002

Data Index: 649044 (C4 (Web Text))

Max Activating Token Index: 362

Text #9

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0746. Min Act: -0.0003

Data Index: 493105 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0704. Min Act: -0.0003

Data Index: 922793 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0688. Min Act: -0.0002

Data Index: 1009624 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0734. Min Act: -0.0002

Data Index: 1114861 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0699. Min Act: -0.0002

Data Index: 718910 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0765. Min Act: -0.0002

Data Index: 1262660 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0699. Min Act: -0.0003

Data Index: 1308039 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0671. Min Act: -0.0002

Data Index: 743558 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0766. Min Act: -0.0003

Data Index: 44827 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0746. Min Act: -0.0003

Data Index: 791962 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0697. Min Act: -0.0003

Data Index: 990758 (C4 (Web Text))

Max Activating Token Index: 1013