Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3208 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.1021. Min Act: -0.0002

Data Index: 1576885 (Python Code)

Max Activating Token Index: 339

Text #1

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0983. Min Act: -0.0001

Data Index: 981320 (C4 (Web Text))

Max Activating Token Index: 847

Text #2

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0934. Min Act: -0.0001

Data Index: 357498 (C4 (Web Text))

Max Activating Token Index: 439

Text #3

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0848. Min Act: -0.0001

Data Index: 1018943 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0913. Min Act: -0.0002

Data Index: 912959 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0862. Min Act: -0.0001

Data Index: 1318595 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0863. Min Act: -0.0002

Data Index: 1121656 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0845. Min Act: -0.0001

Data Index: 1279409 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0799. Min Act: -0.0001

Data Index: 969619 (C4 (Web Text))

Max Activating Token Index: 317

Text #9

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0848. Min Act: -0.0002

Data Index: 1012970 (C4 (Web Text))

Max Activating Token Index: 814

Text #10

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0763. Min Act: -0.0001

Data Index: 940756 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0807. Min Act: -0.0001

Data Index: 502666 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0626. Min Act: -0.0001

Data Index: 450581 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0789. Min Act: -0.0002

Data Index: 500589 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0785. Min Act: -0.0001

Data Index: 1006891 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0723. Min Act: -0.0001

Data Index: 509785 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0694. Min Act: -0.0002

Data Index: 1018965 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0751. Min Act: -0.0001

Data Index: 1068806 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0750. Min Act: -0.0001

Data Index: 409928 (C4 (Web Text))

Max Activating Token Index: 560

Text #19

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0741. Min Act: -0.0001

Data Index: 964412 (C4 (Web Text))

Max Activating Token Index: 276