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

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

Neuron 2226 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.1008. Min Act: -0.0002

Data Index: 1428681 (Python Code)

Max Activating Token Index: 586

Text #1

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0879. Min Act: -0.0002

Data Index: 1490316 (Python Code)

Max Activating Token Index: 495

Text #2

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0828. Min Act: -0.0002

Data Index: 597160 (C4 (Web Text))

Max Activating Token Index: 425

Text #3

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0551. Min Act: -0.0002

Data Index: 507988 (C4 (Web Text))

Max Activating Token Index: 268

Text #4

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0803. Min Act: -0.0002

Data Index: 158286 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0740. Min Act: -0.0002

Data Index: 299743 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0819. Min Act: -0.0002

Data Index: 229942 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0755. Min Act: -0.0002

Data Index: 1548526 (Python Code)

Max Activating Token Index: 357

Text #8

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0756. Min Act: -0.0002

Data Index: 1380359 (Python Code)

Max Activating Token Index: 239

Text #9

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0667. Min Act: -0.0002

Data Index: 16876 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0503. Min Act: -0.0002

Data Index: 374921 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0889. Min Act: -0.0002

Data Index: 1586310 (Python Code)

Max Activating Token Index: 437

Text #12

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0675. Min Act: -0.0002

Data Index: 1587868 (Python Code)

Max Activating Token Index: 865

Text #13

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0512. Min Act: -0.0002

Data Index: 1469152 (Python Code)

Max Activating Token Index: 256

Text #14

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0726. Min Act: -0.0002

Data Index: 1170574 (C4 (Web Text))

Max Activating Token Index: 673

Text #15

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0805. Min Act: -0.0002

Data Index: 395839 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0664. Min Act: -0.0002

Data Index: 625288 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0716. Min Act: -0.0002

Data Index: 324422 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0665. Min Act: -0.0002

Data Index: 1395726 (Python Code)

Max Activating Token Index: 804

Text #19

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0661. Min Act: -0.0002

Data Index: 775144 (C4 (Web Text))

Max Activating Token Index: 519