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

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

Neuron 5969 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0661. Min Act: -0.0002

Data Index: 1327325 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0664. Min Act: -0.0002

Data Index: 599110 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0631. Min Act: -0.0002

Data Index: 856462 (C4 (Web Text))

Max Activating Token Index: 596

Text #3

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0629. Min Act: -0.0002

Data Index: 1324675 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0627. Min Act: -0.0002

Data Index: 925794 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0616. Min Act: -0.0002

Data Index: 993445 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0628. Min Act: -0.0002

Data Index: 610454 (C4 (Web Text))

Max Activating Token Index: 505

Text #7

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0602. Min Act: -0.0002

Data Index: 979036 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0611. Min Act: -0.0002

Data Index: 1134692 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0602. Min Act: -0.0002

Data Index: 1506889 (Python Code)

Max Activating Token Index: 680

Text #10

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0598. Min Act: -0.0003

Data Index: 985214 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0608. Min Act: -0.0002

Data Index: 961715 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0606. Min Act: -0.0002

Data Index: 999835 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0579. Min Act: -0.0002

Data Index: 1374122 (Python Code)

Max Activating Token Index: 329

Text #14

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0583. Min Act: -0.0002

Data Index: 128780 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0578. Min Act: -0.0002

Data Index: 1530486 (Python Code)

Max Activating Token Index: 617

Text #16

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1481844 (Python Code)

Max Activating Token Index: 82

Text #17

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0587. Min Act: -0.0002

Data Index: 1519202 (Python Code)

Max Activating Token Index: 256

Text #18

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0578. Min Act: -0.0002

Data Index: 1006651 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0594. Min Act: -0.0002

Data Index: 788036 (C4 (Web Text))

Max Activating Token Index: 422