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

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

Neuron 709 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.1025. Min Act: -0.0000

Data Index: 1501358 (Python Code)

Max Activating Token Index: 473

Text #1

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0924. Min Act: -0.0000

Data Index: 202464 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0904. Min Act: 0.0001

Data Index: 408178 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0845. Min Act: -0.0000

Data Index: 1503567 (Python Code)

Max Activating Token Index: 871

Text #4

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0936. Min Act: -0.0000

Data Index: 424604 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0865. Min Act: -0.0000

Data Index: 141750 (C4 (Web Text))

Max Activating Token Index: 1001

Text #6

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0842. Min Act: -0.0000

Data Index: 1285147 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0845. Min Act: -0.0000

Data Index: 795118 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0851. Min Act: -0.0000

Data Index: 531826 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0838. Min Act: -0.0000

Data Index: 1144714 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0800. Min Act: -0.0000

Data Index: 604554 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0717. Min Act: -0.0000

Data Index: 1433663 (Python Code)

Max Activating Token Index: 987

Text #12

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0769. Min Act: 0.0000

Data Index: 1478653 (Python Code)

Max Activating Token Index: 363

Text #13

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0727. Min Act: -0.0000

Data Index: 1527695 (Python Code)

Max Activating Token Index: 503

Text #14

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0760. Min Act: -0.0000

Data Index: 554867 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0757. Min Act: -0.0000

Data Index: 687613 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0750. Min Act: -0.0000

Data Index: 1219333 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0719. Min Act: -0.0001

Data Index: 731260 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0768. Min Act: -0.0000

Data Index: 1368925 (Python Code)

Max Activating Token Index: 6

Text #19

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0713. Min Act: -0.0000

Data Index: 185241 (C4 (Web Text))

Max Activating Token Index: 127