Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 915 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.1019. Min Act: -0.0003

Data Index: 1249842 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0902. Min Act: -0.0003

Data Index: 1113590 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.1025. Min Act: -0.0003

Data Index: 428824 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0901. Min Act: -0.0003

Data Index: 331737 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0870. Min Act: -0.0003

Data Index: 1112875 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0909. Min Act: -0.0003

Data Index: 953202 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0820. Min Act: -0.0003

Data Index: 796763 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0759. Min Act: -0.0003

Data Index: 527087 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0846. Min Act: -0.0003

Data Index: 289650 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0782. Min Act: -0.0003

Data Index: 850704 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0909. Min Act: -0.0003

Data Index: 45085 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0803. Min Act: -0.0003

Data Index: 406277 (C4 (Web Text))

Max Activating Token Index: 617

Text #12

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0705. Min Act: -0.0003

Data Index: 513002 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0775. Min Act: -0.0003

Data Index: 748195 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0800. Min Act: -0.0003

Data Index: 235871 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0822. Min Act: -0.0003

Data Index: 1205534 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0751. Min Act: -0.0003

Data Index: 768633 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0807. Min Act: -0.0003

Data Index: 195940 (C4 (Web Text))

Max Activating Token Index: 726

Text #18

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0756. Min Act: -0.0003

Data Index: 661106 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0791. Min Act: -0.0003

Data Index: 1327622 (C4 (Web Text))

Max Activating Token Index: 886