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

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

Neuron 3928 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.8809. Min Act: -0.0000

Data Index: 1620800 (Python Code)

Max Activating Token Index: 708

Text #1

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.9242. Min Act: -0.0000

Data Index: 1587847 (Python Code)

Max Activating Token Index: 1009

Text #2

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.8120. Min Act: -0.0000

Data Index: 1365566 (Python Code)

Max Activating Token Index: 64

Text #3

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.8249. Min Act: -0.0000

Data Index: 1546468 (Python Code)

Max Activating Token Index: 834

Text #4

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.7509. Min Act: -0.0000

Data Index: 1363091 (Python Code)

Max Activating Token Index: 146

Text #5

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.7629. Min Act: -0.0000

Data Index: 1571507 (Python Code)

Max Activating Token Index: 608

Text #6

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.7321. Min Act: -0.0000

Data Index: 1575721 (Python Code)

Max Activating Token Index: 1016

Text #7

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.7052. Min Act: -0.0000

Data Index: 1091908 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.7376. Min Act: -0.0000

Data Index: 1648220 (Python Code)

Max Activating Token Index: 431

Text #9

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.7596. Min Act: -0.0000

Data Index: 1473123 (Python Code)

Max Activating Token Index: 651

Text #10

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.6896. Min Act: -0.0000

Data Index: 1439362 (Python Code)

Max Activating Token Index: 261

Text #11

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.7065. Min Act: -0.0000

Data Index: 1584751 (Python Code)

Max Activating Token Index: 948

Text #12

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.7354. Min Act: -0.0000

Data Index: 1040157 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.7102. Min Act: -0.0000

Data Index: 1484233 (Python Code)

Max Activating Token Index: 584

Text #14

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.6821. Min Act: -0.0000

Data Index: 1555445 (Python Code)

Max Activating Token Index: 770

Text #15

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.7406. Min Act: -0.0000

Data Index: 486418 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.6964. Min Act: -0.0000

Data Index: 979929 (C4 (Web Text))

Max Activating Token Index: 291

Text #17

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.6897. Min Act: -0.0000

Data Index: 1479852 (Python Code)

Max Activating Token Index: 637

Text #18

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.6695. Min Act: -0.0000

Data Index: 264464 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.6880. Min Act: -0.0000

Data Index: 1371629 (Python Code)

Max Activating Token Index: 756