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

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

Neuron 366 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: 0.0899. Min Range: -0.0899

Max Act: 0.0809. Min Act: -0.0002

Data Index: 850699 (C4 (Web Text))

Max Activating Token Index: 698

Text #1

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0886. Min Act: -0.0002

Data Index: 965032 (C4 (Web Text))

Max Activating Token Index: 953

Text #2

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0875. Min Act: -0.0002

Data Index: 1262884 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0899. Min Act: -0.0002

Data Index: 570980 (C4 (Web Text))

Max Activating Token Index: 821

Text #4

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0841. Min Act: -0.0002

Data Index: 90301 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0768. Min Act: -0.0002

Data Index: 395343 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0765. Min Act: -0.0002

Data Index: 40680 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0789. Min Act: -0.0002

Data Index: 1104023 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0797. Min Act: -0.0002

Data Index: 19856 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0807. Min Act: -0.0002

Data Index: 698817 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0751. Min Act: -0.0002

Data Index: 1263980 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0780. Min Act: -0.0002

Data Index: 338750 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0701. Min Act: -0.0002

Data Index: 1273213 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0709. Min Act: -0.0002

Data Index: 1093328 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0740. Min Act: -0.0002

Data Index: 350767 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0684. Min Act: -0.0002

Data Index: 73067 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0704. Min Act: -0.0002

Data Index: 790837 (C4 (Web Text))

Max Activating Token Index: 952

Text #17

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0685. Min Act: -0.0002

Data Index: 999066 (C4 (Web Text))

Max Activating Token Index: 903

Text #18

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0662. Min Act: -0.0002

Data Index: 957112 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0723. Min Act: -0.0002

Data Index: 1005821 (C4 (Web Text))

Max Activating Token Index: 886