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

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

Neuron 18 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: 0.0927. Min Range: -0.0927

Max Act: 0.0927. Min Act: -0.0002

Data Index: 784405 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0886. Min Act: -0.0002

Data Index: 962594 (C4 (Web Text))

Max Activating Token Index: 852

Text #2

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0827. Min Act: -0.0002

Data Index: 337410 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0786. Min Act: -0.0002

Data Index: 890076 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0763. Min Act: -0.0002

Data Index: 232645 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0768. Min Act: -0.0002

Data Index: 134235 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0781. Min Act: -0.0002

Data Index: 98923 (C4 (Web Text))

Max Activating Token Index: 368

Text #7

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0826. Min Act: -0.0002

Data Index: 890750 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0710. Min Act: -0.0002

Data Index: 1311772 (C4 (Web Text))

Max Activating Token Index: 523

Text #9

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0690. Min Act: -0.0002

Data Index: 450189 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0757. Min Act: -0.0002

Data Index: 1266818 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0734. Min Act: -0.0002

Data Index: 696983 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0774. Min Act: -0.0002

Data Index: 953901 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0714. Min Act: -0.0002

Data Index: 513117 (C4 (Web Text))

Max Activating Token Index: 346

Text #14

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0755. Min Act: -0.0002

Data Index: 152278 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0707. Min Act: -0.0002

Data Index: 1333592 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0691. Min Act: -0.0002

Data Index: 439101 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0726. Min Act: -0.0002

Data Index: 271687 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0649. Min Act: -0.0002

Data Index: 738097 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0691. Min Act: -0.0002

Data Index: 416039 (C4 (Web Text))

Max Activating Token Index: 152