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

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

Neuron 3429 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0851. Min Act: -0.0001

Data Index: 625970 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0898. Min Act: -0.0001

Data Index: 365435 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0822. Min Act: -0.0001

Data Index: 1036343 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0848. Min Act: -0.0001

Data Index: 933543 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0804. Min Act: -0.0001

Data Index: 660455 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0817. Min Act: -0.0001

Data Index: 878872 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0668. Min Act: -0.0001

Data Index: 250486 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0891. Min Act: -0.0001

Data Index: 492743 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0752. Min Act: -0.0001

Data Index: 664131 (C4 (Web Text))

Max Activating Token Index: 733

Text #9

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0735. Min Act: -0.0001

Data Index: 1254843 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0749. Min Act: -0.0001

Data Index: 733965 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0700. Min Act: -0.0001

Data Index: 1180072 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0764. Min Act: -0.0001

Data Index: 590096 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0718. Min Act: -0.0001

Data Index: 71839 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0741. Min Act: -0.0001

Data Index: 167130 (C4 (Web Text))

Max Activating Token Index: 731

Text #15

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0768. Min Act: -0.0001

Data Index: 990745 (C4 (Web Text))

Max Activating Token Index: 631

Text #16

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0714. Min Act: -0.0001

Data Index: 98757 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0637. Min Act: -0.0001

Data Index: 873571 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0688. Min Act: -0.0001

Data Index: 1163236 (C4 (Web Text))

Max Activating Token Index: 845

Text #19

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0662. Min Act: -0.0001

Data Index: 571125 (C4 (Web Text))

Max Activating Token Index: 678