Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5318 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.1021. Min Act: -0.0002

Data Index: 823400 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0995. Min Act: -0.0002

Data Index: 151094 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0745. Min Act: -0.0002

Data Index: 536551 (C4 (Web Text))

Max Activating Token Index: 413

Text #3

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0815. Min Act: -0.0001

Data Index: 552908 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0895. Min Act: -0.0001

Data Index: 750009 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0720. Min Act: -0.0002

Data Index: 158677 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0681. Min Act: -0.0001

Data Index: 865229 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0630. Min Act: -0.0001

Data Index: 246941 (C4 (Web Text))

Max Activating Token Index: 512

Text #8

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0623. Min Act: -0.0001

Data Index: 102963 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0753. Min Act: -0.0001

Data Index: 246570 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0670. Min Act: -0.0002

Data Index: 46792 (C4 (Web Text))

Max Activating Token Index: 444

Text #11

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0631. Min Act: -0.0001

Data Index: 21048 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0670. Min Act: -0.0001

Data Index: 825533 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0576. Min Act: -0.0001

Data Index: 466392 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0624. Min Act: -0.0001

Data Index: 1069888 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0645. Min Act: -0.0001

Data Index: 820969 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0526. Min Act: -0.0001

Data Index: 421191 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0506. Min Act: -0.0001

Data Index: 1556371 (Python Code)

Max Activating Token Index: 183

Text #18

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0655. Min Act: -0.0002

Data Index: 1148890 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0583. Min Act: -0.0001

Data Index: 1474777 (Python Code)

Max Activating Token Index: 122