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

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

Neuron 4021 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2922. Min Range: -1.2922

Max Act: 1.2922. Min Act: -0.0000

Data Index: 1541278 (Python Code)

Max Activating Token Index: 318

Text #1

Max Range: 1.2922. Min Range: -1.2922

Max Act: 1.0496. Min Act: -0.0000

Data Index: 1488653 (Python Code)

Max Activating Token Index: 20

Text #2

Max Range: 1.2922. Min Range: -1.2922

Max Act: 1.0642. Min Act: -0.0000

Data Index: 1365962 (Python Code)

Max Activating Token Index: 247

Text #3

Max Range: 1.2922. Min Range: -1.2922

Max Act: 1.0024. Min Act: -0.0000

Data Index: 1421792 (Python Code)

Max Activating Token Index: 387

Text #4

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.9339. Min Act: -0.0000

Data Index: 1537918 (Python Code)

Max Activating Token Index: 232

Text #5

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.9185. Min Act: -0.0000

Data Index: 1475002 (Python Code)

Max Activating Token Index: 783

Text #6

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.9198. Min Act: -0.0000

Data Index: 1611660 (Python Code)

Max Activating Token Index: 846

Text #7

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.8668. Min Act: -0.0000

Data Index: 1373218 (Python Code)

Max Activating Token Index: 106

Text #8

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.9185. Min Act: -0.0000

Data Index: 1424805 (Python Code)

Max Activating Token Index: 326

Text #9

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.8531. Min Act: -0.0000

Data Index: 1619516 (Python Code)

Max Activating Token Index: 944

Text #10

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.9274. Min Act: -0.0000

Data Index: 1483709 (Python Code)

Max Activating Token Index: 231

Text #11

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.9508. Min Act: -0.0000

Data Index: 1474300 (Python Code)

Max Activating Token Index: 666

Text #12

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.8274. Min Act: -0.0000

Data Index: 1595844 (Python Code)

Max Activating Token Index: 508

Text #13

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.8562. Min Act: 0.0000

Data Index: 1551695 (Python Code)

Max Activating Token Index: 926

Text #14

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.8281. Min Act: -0.0000

Data Index: 1451312 (Python Code)

Max Activating Token Index: 1002

Text #15

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.8032. Min Act: -0.0000

Data Index: 1480771 (Python Code)

Max Activating Token Index: 780

Text #16

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.8107. Min Act: -0.0000

Data Index: 1420789 (Python Code)

Max Activating Token Index: 629

Text #17

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.8487. Min Act: -0.0000

Data Index: 1491101 (Python Code)

Max Activating Token Index: 275

Text #18

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.7734. Min Act: -0.0000

Data Index: 1656464 (Python Code)

Max Activating Token Index: 41

Text #19

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.7889. Min Act: -0.0000

Data Index: 1584309 (Python Code)

Max Activating Token Index: 439