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

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

Neuron 2588 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.5532. Min Range: -6.5532

Max Act: 6.4791. Min Act: -0.0000

Data Index: 1432954 (Python Code)

Max Activating Token Index: 193

Text #1

Max Range: 6.5532. Min Range: -6.5532

Max Act: 6.4720. Min Act: -0.0000

Data Index: 1396389 (Python Code)

Max Activating Token Index: 211

Text #2

Max Range: 6.5532. Min Range: -6.5532

Max Act: 6.1951. Min Act: -0.0000

Data Index: 1547109 (Python Code)

Max Activating Token Index: 939

Text #3

Max Range: 6.5532. Min Range: -6.5532

Max Act: 6.5532. Min Act: -0.0000

Data Index: 1432605 (Python Code)

Max Activating Token Index: 572

Text #4

Max Range: 6.5532. Min Range: -6.5532

Max Act: 6.0359. Min Act: -0.0000

Data Index: 1545281 (Python Code)

Max Activating Token Index: 923

Text #5

Max Range: 6.5532. Min Range: -6.5532

Max Act: 5.8646. Min Act: -0.0000

Data Index: 862977 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 6.5532. Min Range: -6.5532

Max Act: 4.6033. Min Act: -0.0000

Data Index: 1576115 (Python Code)

Max Activating Token Index: 695

Text #7

Max Range: 6.5532. Min Range: -6.5532

Max Act: 4.5757. Min Act: -0.0000

Data Index: 1412589 (Python Code)

Max Activating Token Index: 636

Text #8

Max Range: 6.5532. Min Range: -6.5532

Max Act: 4.5580. Min Act: -0.0000

Data Index: 1528328 (Python Code)

Max Activating Token Index: 241

Text #9

Max Range: 6.5532. Min Range: -6.5532

Max Act: 4.9176. Min Act: -0.0000

Data Index: 1423091 (Python Code)

Max Activating Token Index: 373

Text #10

Max Range: 6.5532. Min Range: -6.5532

Max Act: 5.0825. Min Act: -0.0000

Data Index: 1391929 (Python Code)

Max Activating Token Index: 894

Text #11

Max Range: 6.5532. Min Range: -6.5532

Max Act: 4.5686. Min Act: -0.0000

Data Index: 1528505 (Python Code)

Max Activating Token Index: 559

Text #12

Max Range: 6.5532. Min Range: -6.5532

Max Act: 4.3968. Min Act: -0.0000

Data Index: 1655121 (Python Code)

Max Activating Token Index: 855

Text #13

Max Range: 6.5532. Min Range: -6.5532

Max Act: 4.1892. Min Act: -0.0000

Data Index: 1479339 (Python Code)

Max Activating Token Index: 833

Text #14

Max Range: 6.5532. Min Range: -6.5532

Max Act: 4.2980. Min Act: -0.0000

Data Index: 1567633 (Python Code)

Max Activating Token Index: 163

Text #15

Max Range: 6.5532. Min Range: -6.5532

Max Act: 4.2704. Min Act: -0.0000

Data Index: 1643784 (Python Code)

Max Activating Token Index: 38

Text #16

Max Range: 6.5532. Min Range: -6.5532

Max Act: 4.5615. Min Act: -0.0000

Data Index: 1425097 (Python Code)

Max Activating Token Index: 837

Text #17

Max Range: 6.5532. Min Range: -6.5532

Max Act: 4.4126. Min Act: -0.0000

Data Index: 1622388 (Python Code)

Max Activating Token Index: 687

Text #18

Max Range: 6.5532. Min Range: -6.5532

Max Act: 4.3974. Min Act: -0.0000

Data Index: 1614997 (Python Code)

Max Activating Token Index: 712

Text #19

Max Range: 6.5532. Min Range: -6.5532

Max Act: 4.2109. Min Act: -0.0000

Data Index: 1608320 (Python Code)

Max Activating Token Index: 1013