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

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

Neuron 3907 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: 0.0905. Min Range: -0.0905

Max Act: 0.0905. Min Act: -0.0002

Data Index: 709243 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0831. Min Act: -0.0002

Data Index: 1548614 (Python Code)

Max Activating Token Index: 311

Text #2

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0843. Min Act: -0.0002

Data Index: 1402950 (Python Code)

Max Activating Token Index: 365

Text #3

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0823. Min Act: -0.0002

Data Index: 1557531 (Python Code)

Max Activating Token Index: 547

Text #4

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0770. Min Act: -0.0002

Data Index: 1568266 (Python Code)

Max Activating Token Index: 74

Text #5

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0770. Min Act: -0.0002

Data Index: 1471659 (Python Code)

Max Activating Token Index: 804

Text #6

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0765. Min Act: -0.0002

Data Index: 1456321 (Python Code)

Max Activating Token Index: 428

Text #7

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0756. Min Act: -0.0002

Data Index: 757222 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0746. Min Act: -0.0002

Data Index: 1489202 (Python Code)

Max Activating Token Index: 895

Text #9

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0746. Min Act: -0.0002

Data Index: 1424396 (Python Code)

Max Activating Token Index: 202

Text #10

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0714. Min Act: -0.0002

Data Index: 1515818 (Python Code)

Max Activating Token Index: 491

Text #11

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0731. Min Act: -0.0002

Data Index: 1479915 (Python Code)

Max Activating Token Index: 373

Text #12

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0714. Min Act: -0.0002

Data Index: 1507169 (Python Code)

Max Activating Token Index: 64

Text #13

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0688. Min Act: -0.0002

Data Index: 1564098 (Python Code)

Max Activating Token Index: 210

Text #14

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0708. Min Act: -0.0002

Data Index: 1369484 (Python Code)

Max Activating Token Index: 484

Text #15

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0705. Min Act: -0.0002

Data Index: 1505575 (Python Code)

Max Activating Token Index: 20

Text #16

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0676. Min Act: -0.0002

Data Index: 1652987 (Python Code)

Max Activating Token Index: 29

Text #17

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0699. Min Act: -0.0002

Data Index: 1464666 (Python Code)

Max Activating Token Index: 561

Text #18

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0699. Min Act: -0.0002

Data Index: 1469053 (Python Code)

Max Activating Token Index: 53

Text #19

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0695. Min Act: -0.0002

Data Index: 1609364 (Python Code)

Max Activating Token Index: 631