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

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

Neuron 4018 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6733. Min Range: -1.6733

Max Act: 1.6733. Min Act: -0.0000

Data Index: 1632661 (Python Code)

Max Activating Token Index: 819

Text #1

Max Range: 1.6733. Min Range: -1.6733

Max Act: 1.1988. Min Act: -0.0001

Data Index: 1636477 (Python Code)

Max Activating Token Index: 959

Text #2

Max Range: 1.6733. Min Range: -1.6733

Max Act: 1.2509. Min Act: -0.0000

Data Index: 1486970 (Python Code)

Max Activating Token Index: 586

Text #3

Max Range: 1.6733. Min Range: -1.6733

Max Act: 1.1124. Min Act: -0.0000

Data Index: 1474858 (Python Code)

Max Activating Token Index: 140

Text #4

Max Range: 1.6733. Min Range: -1.6733

Max Act: 1.0269. Min Act: -0.0000

Data Index: 1547328 (Python Code)

Max Activating Token Index: 658

Text #5

Max Range: 1.6733. Min Range: -1.6733

Max Act: 1.0543. Min Act: -0.0000

Data Index: 1635050 (Python Code)

Max Activating Token Index: 123

Text #6

Max Range: 1.6733. Min Range: -1.6733

Max Act: 1.0755. Min Act: -0.0000

Data Index: 1562218 (Python Code)

Max Activating Token Index: 727

Text #7

Max Range: 1.6733. Min Range: -1.6733

Max Act: 1.0338. Min Act: -0.0000

Data Index: 1506024 (Python Code)

Max Activating Token Index: 1005

Text #8

Max Range: 1.6733. Min Range: -1.6733

Max Act: 1.0223. Min Act: -0.0000

Data Index: 1654871 (Python Code)

Max Activating Token Index: 665

Text #9

Max Range: 1.6733. Min Range: -1.6733

Max Act: 0.9403. Min Act: -0.0000

Data Index: 1585943 (Python Code)

Max Activating Token Index: 739

Text #10

Max Range: 1.6733. Min Range: -1.6733

Max Act: 1.0009. Min Act: -0.0000

Data Index: 1557473 (Python Code)

Max Activating Token Index: 97

Text #11

Max Range: 1.6733. Min Range: -1.6733

Max Act: 1.0162. Min Act: -0.0000

Data Index: 1568960 (Python Code)

Max Activating Token Index: 321

Text #12

Max Range: 1.6733. Min Range: -1.6733

Max Act: 1.0127. Min Act: -0.0000

Data Index: 1498655 (Python Code)

Max Activating Token Index: 369

Text #13

Max Range: 1.6733. Min Range: -1.6733

Max Act: 0.9718. Min Act: -0.0000

Data Index: 1366112 (Python Code)

Max Activating Token Index: 247

Text #14

Max Range: 1.6733. Min Range: -1.6733

Max Act: 0.9767. Min Act: -0.0000

Data Index: 1519554 (Python Code)

Max Activating Token Index: 997

Text #15

Max Range: 1.6733. Min Range: -1.6733

Max Act: 0.9436. Min Act: -0.0000

Data Index: 1624035 (Python Code)

Max Activating Token Index: 235

Text #16

Max Range: 1.6733. Min Range: -1.6733

Max Act: 0.9648. Min Act: -0.0000

Data Index: 1433898 (Python Code)

Max Activating Token Index: 246

Text #17

Max Range: 1.6733. Min Range: -1.6733

Max Act: 0.9811. Min Act: -0.0000

Data Index: 1395531 (Python Code)

Max Activating Token Index: 810

Text #18

Max Range: 1.6733. Min Range: -1.6733

Max Act: 0.9824. Min Act: -0.0000

Data Index: 1410788 (Python Code)

Max Activating Token Index: 719

Text #19

Max Range: 1.6733. Min Range: -1.6733

Max Act: 1.0675. Min Act: -0.0000

Data Index: 1576315 (Python Code)

Max Activating Token Index: 785