Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1139 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0918. Min Act: -0.0003

Data Index: 814936 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0873. Min Act: -0.0003

Data Index: 665831 (C4 (Web Text))

Max Activating Token Index: 489

Text #2

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0808. Min Act: -0.0002

Data Index: 485427 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0814. Min Act: -0.0003

Data Index: 982869 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0823. Min Act: -0.0003

Data Index: 1333548 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0868. Min Act: -0.0002

Data Index: 1203262 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0767. Min Act: -0.0003

Data Index: 626828 (C4 (Web Text))

Max Activating Token Index: 674

Text #7

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0773. Min Act: -0.0003

Data Index: 1350441 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0775. Min Act: -0.0003

Data Index: 570154 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0760. Min Act: -0.0002

Data Index: 1015491 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0758. Min Act: -0.0003

Data Index: 1323336 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0743. Min Act: -0.0003

Data Index: 335430 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0775. Min Act: -0.0002

Data Index: 138362 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0735. Min Act: -0.0003

Data Index: 837442 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0736. Min Act: -0.0003

Data Index: 910982 (C4 (Web Text))

Max Activating Token Index: 753

Text #15

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0721. Min Act: -0.0000

Data Index: 1088863 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0729. Min Act: -0.0003

Data Index: 1230497 (C4 (Web Text))

Max Activating Token Index: 992

Text #17

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0716. Min Act: -0.0000

Data Index: 772190 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0710. Min Act: -0.0003

Data Index: 1274213 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0710. Min Act: -0.0002

Data Index: 1163771 (C4 (Web Text))

Max Activating Token Index: 336