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

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

Neuron 4527 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.9088. Min Act: -0.0000

Data Index: 1454241 (Python Code)

Max Activating Token Index: 427

Text #1

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.7819. Min Act: -0.0000

Data Index: 1579196 (Python Code)

Max Activating Token Index: 567

Text #2

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.7436. Min Act: -0.0000

Data Index: 1471537 (Python Code)

Max Activating Token Index: 274

Text #3

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.6712. Min Act: -0.0000

Data Index: 1596463 (Python Code)

Max Activating Token Index: 127

Text #4

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.5672. Min Act: -0.0000

Data Index: 1640808 (Python Code)

Max Activating Token Index: 98

Text #5

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.6245. Min Act: -0.0000

Data Index: 1463402 (Python Code)

Max Activating Token Index: 44

Text #6

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.6291. Min Act: -0.0000

Data Index: 1544524 (Python Code)

Max Activating Token Index: 896

Text #7

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.5887. Min Act: -0.0000

Data Index: 1572249 (Python Code)

Max Activating Token Index: 880

Text #8

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.5153. Min Act: -0.0000

Data Index: 1557929 (Python Code)

Max Activating Token Index: 299

Text #9

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.5902. Min Act: -0.0000

Data Index: 1397428 (Python Code)

Max Activating Token Index: 148

Text #10

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.4931. Min Act: -0.0000

Data Index: 1613829 (Python Code)

Max Activating Token Index: 80

Text #11

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.5752. Min Act: -0.0000

Data Index: 1651149 (Python Code)

Max Activating Token Index: 748

Text #12

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.5727. Min Act: -0.0000

Data Index: 1513971 (Python Code)

Max Activating Token Index: 213

Text #13

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.5859. Min Act: -0.0000

Data Index: 1503642 (Python Code)

Max Activating Token Index: 746

Text #14

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.5529. Min Act: -0.0000

Data Index: 1632138 (Python Code)

Max Activating Token Index: 295

Text #15

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.5742. Min Act: -0.0000

Data Index: 1532346 (Python Code)

Max Activating Token Index: 735

Text #16

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.4536. Min Act: -0.0000

Data Index: 1493474 (Python Code)

Max Activating Token Index: 822

Text #17

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.4735. Min Act: -0.0000

Data Index: 1458994 (Python Code)

Max Activating Token Index: 36

Text #18

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.4982. Min Act: -0.0000

Data Index: 1521438 (Python Code)

Max Activating Token Index: 825

Text #19

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.5678. Min Act: -0.0000

Data Index: 1377613 (Python Code)

Max Activating Token Index: 81