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

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

Neuron 3877 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9837. Min Range: -1.9837

Max Act: 1.8089. Min Act: -0.0000

Data Index: 1648934 (Python Code)

Max Activating Token Index: 816

Text #1

Max Range: 1.9837. Min Range: -1.9837

Max Act: 1.7522. Min Act: -0.0000

Data Index: 1370612 (Python Code)

Max Activating Token Index: 749

Text #2

Max Range: 1.9837. Min Range: -1.9837

Max Act: 1.9837. Min Act: -0.0000

Data Index: 1619495 (Python Code)

Max Activating Token Index: 55

Text #3

Max Range: 1.9837. Min Range: -1.9837

Max Act: 1.8989. Min Act: -0.0000

Data Index: 1615242 (Python Code)

Max Activating Token Index: 809

Text #4

Max Range: 1.9837. Min Range: -1.9837

Max Act: 1.7972. Min Act: -0.0000

Data Index: 1573432 (Python Code)

Max Activating Token Index: 839

Text #5

Max Range: 1.9837. Min Range: -1.9837

Max Act: 1.8982. Min Act: -0.0000

Data Index: 1430924 (Python Code)

Max Activating Token Index: 1019

Text #6

Max Range: 1.9837. Min Range: -1.9837

Max Act: 1.7495. Min Act: -0.0000

Data Index: 485603 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 1.9837. Min Range: -1.9837

Max Act: 1.7915. Min Act: -0.0000

Data Index: 1242082 (C4 (Web Text))

Max Activating Token Index: 686

Text #8

Max Range: 1.9837. Min Range: -1.9837

Max Act: 1.6383. Min Act: -0.0000

Data Index: 1459205 (Python Code)

Max Activating Token Index: 726

Text #9

Max Range: 1.9837. Min Range: -1.9837

Max Act: 1.7117. Min Act: -0.0000

Data Index: 1505093 (Python Code)

Max Activating Token Index: 686

Text #10

Max Range: 1.9837. Min Range: -1.9837

Max Act: 1.6273. Min Act: -0.0000

Data Index: 1655203 (Python Code)

Max Activating Token Index: 631

Text #11

Max Range: 1.9837. Min Range: -1.9837

Max Act: 1.7988. Min Act: -0.0000

Data Index: 1497903 (Python Code)

Max Activating Token Index: 439

Text #12

Max Range: 1.9837. Min Range: -1.9837

Max Act: 1.5712. Min Act: -0.0000

Data Index: 1362284 (Python Code)

Max Activating Token Index: 692

Text #13

Max Range: 1.9837. Min Range: -1.9837

Max Act: 1.5178. Min Act: -0.0000

Data Index: 1590866 (Python Code)

Max Activating Token Index: 805

Text #14

Max Range: 1.9837. Min Range: -1.9837

Max Act: 1.6914. Min Act: -0.0000

Data Index: 1592805 (Python Code)

Max Activating Token Index: 755

Text #15

Max Range: 1.9837. Min Range: -1.9837

Max Act: 1.6764. Min Act: -0.0000

Data Index: 1361172 (Python Code)

Max Activating Token Index: 578

Text #16

Max Range: 1.9837. Min Range: -1.9837

Max Act: 1.5495. Min Act: -0.0000

Data Index: 1456336 (Python Code)

Max Activating Token Index: 828

Text #17

Max Range: 1.9837. Min Range: -1.9837

Max Act: 1.6446. Min Act: -0.0000

Data Index: 1385779 (Python Code)

Max Activating Token Index: 970

Text #18

Max Range: 1.9837. Min Range: -1.9837

Max Act: 1.6252. Min Act: -0.0000

Data Index: 1488904 (Python Code)

Max Activating Token Index: 605

Text #19

Max Range: 1.9837. Min Range: -1.9837

Max Act: 1.7830. Min Act: -0.0000

Data Index: 1534655 (Python Code)

Max Activating Token Index: 825