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

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

Neuron 4424 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.3211. Min Act: -0.0000

Data Index: 1567181 (Python Code)

Max Activating Token Index: 914

Text #1

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2870. Min Act: -0.0000

Data Index: 970896 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.3003. Min Act: -0.0000

Data Index: 371595 (C4 (Web Text))

Max Activating Token Index: 248

Text #3

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.3121. Min Act: -0.0000

Data Index: 1410499 (Python Code)

Max Activating Token Index: 134

Text #4

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2747. Min Act: -0.0000

Data Index: 1526168 (Python Code)

Max Activating Token Index: 643

Text #5

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2929. Min Act: -0.0000

Data Index: 1477174 (Python Code)

Max Activating Token Index: 220

Text #6

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2848. Min Act: -0.0000

Data Index: 1443099 (Python Code)

Max Activating Token Index: 65

Text #7

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2830. Min Act: -0.0000

Data Index: 1495616 (Python Code)

Max Activating Token Index: 61

Text #8

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2805. Min Act: -0.0000

Data Index: 373018 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2886. Min Act: -0.0000

Data Index: 1650183 (Python Code)

Max Activating Token Index: 539

Text #10

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2764. Min Act: -0.0000

Data Index: 1621216 (Python Code)

Max Activating Token Index: 420

Text #11

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2675. Min Act: -0.0000

Data Index: 1598653 (Python Code)

Max Activating Token Index: 37

Text #12

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2665. Min Act: -0.0000

Data Index: 1525976 (Python Code)

Max Activating Token Index: 737

Text #13

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2877. Min Act: -0.0000

Data Index: 1517458 (Python Code)

Max Activating Token Index: 400

Text #14

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2723. Min Act: -0.0000

Data Index: 1518764 (Python Code)

Max Activating Token Index: 143

Text #15

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2710. Min Act: -0.0000

Data Index: 1380618 (Python Code)

Max Activating Token Index: 54

Text #16

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2659. Min Act: -0.0000

Data Index: 1580321 (Python Code)

Max Activating Token Index: 735

Text #17

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2642. Min Act: -0.0000

Data Index: 454501 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2612. Min Act: -0.0000

Data Index: 1647215 (Python Code)

Max Activating Token Index: 779

Text #19

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2783. Min Act: -0.0000

Data Index: 1411823 (Python Code)

Max Activating Token Index: 794