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

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

Neuron 6001 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5375. Min Range: -2.5375

Max Act: 2.5375. Min Act: -0.0000

Data Index: 1632519 (Python Code)

Max Activating Token Index: 352

Text #1

Max Range: 2.5375. Min Range: -2.5375

Max Act: 2.4664. Min Act: -0.0000

Data Index: 1405647 (Python Code)

Max Activating Token Index: 639

Text #2

Max Range: 2.5375. Min Range: -2.5375

Max Act: 2.4011. Min Act: 0.0000

Data Index: 1602255 (Python Code)

Max Activating Token Index: 885

Text #3

Max Range: 2.5375. Min Range: -2.5375

Max Act: 2.3397. Min Act: 0.0000

Data Index: 1514249 (Python Code)

Max Activating Token Index: 48

Text #4

Max Range: 2.5375. Min Range: -2.5375

Max Act: 2.3339. Min Act: 0.0000

Data Index: 1391149 (Python Code)

Max Activating Token Index: 799

Text #5

Max Range: 2.5375. Min Range: -2.5375

Max Act: 2.1739. Min Act: -0.0000

Data Index: 1615954 (Python Code)

Max Activating Token Index: 39

Text #6

Max Range: 2.5375. Min Range: -2.5375

Max Act: 2.1127. Min Act: 0.0000

Data Index: 1437873 (Python Code)

Max Activating Token Index: 451

Text #7

Max Range: 2.5375. Min Range: -2.5375

Max Act: 2.1032. Min Act: -0.0000

Data Index: 1556246 (Python Code)

Max Activating Token Index: 917

Text #8

Max Range: 2.5375. Min Range: -2.5375

Max Act: 2.0483. Min Act: 0.0000

Data Index: 1473523 (Python Code)

Max Activating Token Index: 195

Text #9

Max Range: 2.5375. Min Range: -2.5375

Max Act: 2.0357. Min Act: -0.0000

Data Index: 1501707 (Python Code)

Max Activating Token Index: 303

Text #10

Max Range: 2.5375. Min Range: -2.5375

Max Act: 1.9781. Min Act: 0.0000

Data Index: 1625562 (Python Code)

Max Activating Token Index: 264

Text #11

Max Range: 2.5375. Min Range: -2.5375

Max Act: 1.9638. Min Act: -0.0000

Data Index: 1513979 (Python Code)

Max Activating Token Index: 658

Text #12

Max Range: 2.5375. Min Range: -2.5375

Max Act: 2.0853. Min Act: -0.0000

Data Index: 1380520 (Python Code)

Max Activating Token Index: 734

Text #13

Max Range: 2.5375. Min Range: -2.5375

Max Act: 1.9351. Min Act: -0.0000

Data Index: 1641697 (Python Code)

Max Activating Token Index: 791

Text #14

Max Range: 2.5375. Min Range: -2.5375

Max Act: 1.8866. Min Act: -0.0000

Data Index: 1638082 (Python Code)

Max Activating Token Index: 955

Text #15

Max Range: 2.5375. Min Range: -2.5375

Max Act: 1.8867. Min Act: 0.0000

Data Index: 1387446 (Python Code)

Max Activating Token Index: 947

Text #16

Max Range: 2.5375. Min Range: -2.5375

Max Act: 1.8762. Min Act: -0.0000

Data Index: 1393305 (Python Code)

Max Activating Token Index: 728

Text #17

Max Range: 2.5375. Min Range: -2.5375

Max Act: 1.8602. Min Act: -0.0000

Data Index: 415778 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 2.5375. Min Range: -2.5375

Max Act: 1.7640. Min Act: 0.0000

Data Index: 1580535 (Python Code)

Max Activating Token Index: 830

Text #19

Max Range: 2.5375. Min Range: -2.5375

Max Act: 1.8600. Min Act: -0.0000

Data Index: 1570782 (Python Code)

Max Activating Token Index: 592