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

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

Neuron 1680 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: 0.2082. Min Range: -0.2082

Max Act: 0.2082. Min Act: -0.0002

Data Index: 1364412 (Python Code)

Max Activating Token Index: 726

Text #1

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1862. Min Act: -0.0002

Data Index: 1367446 (Python Code)

Max Activating Token Index: 272

Text #2

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1837. Min Act: -0.0002

Data Index: 1539090 (Python Code)

Max Activating Token Index: 447

Text #3

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1761. Min Act: -0.0002

Data Index: 1545702 (Python Code)

Max Activating Token Index: 84

Text #4

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1774. Min Act: -0.0002

Data Index: 1456795 (Python Code)

Max Activating Token Index: 802

Text #5

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1729. Min Act: -0.0002

Data Index: 1425828 (Python Code)

Max Activating Token Index: 842

Text #6

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1731. Min Act: -0.0002

Data Index: 1630676 (Python Code)

Max Activating Token Index: 448

Text #7

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1741. Min Act: -0.0002

Data Index: 1382123 (Python Code)

Max Activating Token Index: 332

Text #8

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1681. Min Act: -0.0002

Data Index: 1461251 (Python Code)

Max Activating Token Index: 188

Text #9

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1712. Min Act: -0.0002

Data Index: 1480834 (Python Code)

Max Activating Token Index: 217

Text #10

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1666. Min Act: -0.0002

Data Index: 1413121 (Python Code)

Max Activating Token Index: 63

Text #11

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1644. Min Act: -0.0002

Data Index: 1468087 (Python Code)

Max Activating Token Index: 41

Text #12

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1631. Min Act: -0.0002

Data Index: 1362924 (Python Code)

Max Activating Token Index: 396

Text #13

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1560. Min Act: -0.0002

Data Index: 1480015 (Python Code)

Max Activating Token Index: 28

Text #14

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1583. Min Act: -0.0002

Data Index: 1431785 (Python Code)

Max Activating Token Index: 789

Text #15

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1612. Min Act: -0.0002

Data Index: 1466453 (Python Code)

Max Activating Token Index: 62

Text #16

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1599. Min Act: -0.0002

Data Index: 1520401 (Python Code)

Max Activating Token Index: 778

Text #17

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1590. Min Act: -0.0002

Data Index: 1475204 (Python Code)

Max Activating Token Index: 609

Text #18

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1613. Min Act: -0.0002

Data Index: 1603579 (Python Code)

Max Activating Token Index: 360

Text #19

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1598. Min Act: -0.0002

Data Index: 1556921 (Python Code)

Max Activating Token Index: 324