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

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

Neuron 1744 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: 1.8695. Min Range: -1.8695

Max Act: 1.8111. Min Act: -0.0000

Data Index: 1570796 (Python Code)

Max Activating Token Index: 319

Text #1

Max Range: 1.8695. Min Range: -1.8695

Max Act: 1.8695. Min Act: -0.0000

Data Index: 1587318 (Python Code)

Max Activating Token Index: 882

Text #2

Max Range: 1.8695. Min Range: -1.8695

Max Act: 1.5614. Min Act: -0.0000

Data Index: 1543625 (Python Code)

Max Activating Token Index: 395

Text #3

Max Range: 1.8695. Min Range: -1.8695

Max Act: 1.6571. Min Act: -0.0000

Data Index: 1601049 (Python Code)

Max Activating Token Index: 280

Text #4

Max Range: 1.8695. Min Range: -1.8695

Max Act: 1.7457. Min Act: -0.0000

Data Index: 1604343 (Python Code)

Max Activating Token Index: 809

Text #5

Max Range: 1.8695. Min Range: -1.8695

Max Act: 1.5250. Min Act: -0.0000

Data Index: 1479675 (Python Code)

Max Activating Token Index: 582

Text #6

Max Range: 1.8695. Min Range: -1.8695

Max Act: 1.7709. Min Act: -0.0000

Data Index: 1545618 (Python Code)

Max Activating Token Index: 47

Text #7

Max Range: 1.8695. Min Range: -1.8695

Max Act: 1.5035. Min Act: -0.0000

Data Index: 407295 (C4 (Web Text))

Max Activating Token Index: 563

Text #8

Max Range: 1.8695. Min Range: -1.8695

Max Act: 1.5167. Min Act: -0.0000

Data Index: 1444726 (Python Code)

Max Activating Token Index: 392

Text #9

Max Range: 1.8695. Min Range: -1.8695

Max Act: 1.4354. Min Act: -0.0000

Data Index: 1496109 (Python Code)

Max Activating Token Index: 626

Text #10

Max Range: 1.8695. Min Range: -1.8695

Max Act: 1.4757. Min Act: -0.0000

Data Index: 1546667 (Python Code)

Max Activating Token Index: 449

Text #11

Max Range: 1.8695. Min Range: -1.8695

Max Act: 1.7023. Min Act: -0.0000

Data Index: 1565370 (Python Code)

Max Activating Token Index: 25

Text #12

Max Range: 1.8695. Min Range: -1.8695

Max Act: 1.6242. Min Act: -0.0000

Data Index: 1625826 (Python Code)

Max Activating Token Index: 58

Text #13

Max Range: 1.8695. Min Range: -1.8695

Max Act: 1.6777. Min Act: -0.0000

Data Index: 1424880 (Python Code)

Max Activating Token Index: 362

Text #14

Max Range: 1.8695. Min Range: -1.8695

Max Act: 1.3643. Min Act: -0.0000

Data Index: 139681 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 1.8695. Min Range: -1.8695

Max Act: 1.4181. Min Act: -0.0000

Data Index: 1428051 (Python Code)

Max Activating Token Index: 955

Text #16

Max Range: 1.8695. Min Range: -1.8695

Max Act: 1.2950. Min Act: -0.0000

Data Index: 1595689 (Python Code)

Max Activating Token Index: 343

Text #17

Max Range: 1.8695. Min Range: -1.8695

Max Act: 1.7051. Min Act: -0.0000

Data Index: 1394188 (Python Code)

Max Activating Token Index: 301

Text #18

Max Range: 1.8695. Min Range: -1.8695

Max Act: 1.5796. Min Act: -0.0000

Data Index: 1472824 (Python Code)

Max Activating Token Index: 113

Text #19

Max Range: 1.8695. Min Range: -1.8695

Max Act: 1.3328. Min Act: -0.0000

Data Index: 1551508 (Python Code)

Max Activating Token Index: 317