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

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

Neuron 2600 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: 0.0868. Min Range: -0.0868

Max Act: 0.0764. Min Act: -0.0000

Data Index: 1100549 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0868. Min Act: -0.0001

Data Index: 1639503 (Python Code)

Max Activating Token Index: 989

Text #2

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0786. Min Act: -0.0000

Data Index: 1134685 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0744. Min Act: -0.0000

Data Index: 1089482 (C4 (Web Text))

Max Activating Token Index: 440

Text #4

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0728. Min Act: -0.0000

Data Index: 1622206 (Python Code)

Max Activating Token Index: 49

Text #5

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0702. Min Act: -0.0000

Data Index: 1629201 (Python Code)

Max Activating Token Index: 538

Text #6

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0719. Min Act: -0.0000

Data Index: 1509044 (Python Code)

Max Activating Token Index: 47

Text #7

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0683. Min Act: -0.0000

Data Index: 1499707 (Python Code)

Max Activating Token Index: 379

Text #8

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0717. Min Act: -0.0000

Data Index: 1287112 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0687. Min Act: -0.0000

Data Index: 347614 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0633. Min Act: -0.0000

Data Index: 878841 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0669. Min Act: -0.0000

Data Index: 1616551 (Python Code)

Max Activating Token Index: 499

Text #12

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0642. Min Act: -0.0000

Data Index: 1642410 (Python Code)

Max Activating Token Index: 944

Text #13

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0667. Min Act: -0.0000

Data Index: 1423151 (Python Code)

Max Activating Token Index: 349

Text #14

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0604. Min Act: -0.0000

Data Index: 1657049 (Python Code)

Max Activating Token Index: 837

Text #15

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0653. Min Act: -0.0000

Data Index: 68756 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0646. Min Act: -0.0000

Data Index: 1377433 (Python Code)

Max Activating Token Index: 693

Text #17

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0649. Min Act: -0.0000

Data Index: 536916 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0616. Min Act: -0.0000

Data Index: 1538237 (Python Code)

Max Activating Token Index: 570

Text #19

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0600. Min Act: -0.0001

Data Index: 1606892 (Python Code)

Max Activating Token Index: 492