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

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

Neuron 2742 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: 5.5838. Min Range: -5.5838

Max Act: 5.5838. Min Act: -0.0000

Data Index: 1580347 (Python Code)

Max Activating Token Index: 237

Text #1

Max Range: 5.5838. Min Range: -5.5838

Max Act: 5.4189. Min Act: -0.0000

Data Index: 1655132 (Python Code)

Max Activating Token Index: 764

Text #2

Max Range: 5.5838. Min Range: -5.5838

Max Act: 5.1954. Min Act: -0.0000

Data Index: 1481042 (Python Code)

Max Activating Token Index: 381

Text #3

Max Range: 5.5838. Min Range: -5.5838

Max Act: 4.9375. Min Act: -0.0000

Data Index: 1419925 (Python Code)

Max Activating Token Index: 858

Text #4

Max Range: 5.5838. Min Range: -5.5838

Max Act: 5.0537. Min Act: -0.0000

Data Index: 1618661 (Python Code)

Max Activating Token Index: 200

Text #5

Max Range: 5.5838. Min Range: -5.5838

Max Act: 4.5914. Min Act: -0.0000

Data Index: 1517066 (Python Code)

Max Activating Token Index: 265

Text #6

Max Range: 5.5838. Min Range: -5.5838

Max Act: 4.6960. Min Act: -0.0000

Data Index: 1406093 (Python Code)

Max Activating Token Index: 560

Text #7

Max Range: 5.5838. Min Range: -5.5838

Max Act: 4.3372. Min Act: -0.0000

Data Index: 1446590 (Python Code)

Max Activating Token Index: 569

Text #8

Max Range: 5.5838. Min Range: -5.5838

Max Act: 4.4544. Min Act: -0.0000

Data Index: 1432158 (Python Code)

Max Activating Token Index: 460

Text #9

Max Range: 5.5838. Min Range: -5.5838

Max Act: 4.1305. Min Act: -0.0000

Data Index: 1466482 (Python Code)

Max Activating Token Index: 401

Text #10

Max Range: 5.5838. Min Range: -5.5838

Max Act: 4.1059. Min Act: -0.0000

Data Index: 1493886 (Python Code)

Max Activating Token Index: 29

Text #11

Max Range: 5.5838. Min Range: -5.5838

Max Act: 4.0889. Min Act: -0.0000

Data Index: 1520512 (Python Code)

Max Activating Token Index: 945

Text #12

Max Range: 5.5838. Min Range: -5.5838

Max Act: 4.0053. Min Act: -0.0000

Data Index: 1369916 (Python Code)

Max Activating Token Index: 149

Text #13

Max Range: 5.5838. Min Range: -5.5838

Max Act: 3.9914. Min Act: -0.0000

Data Index: 1559174 (Python Code)

Max Activating Token Index: 341

Text #14

Max Range: 5.5838. Min Range: -5.5838

Max Act: 3.6936. Min Act: -0.0000

Data Index: 1497435 (Python Code)

Max Activating Token Index: 293

Text #15

Max Range: 5.5838. Min Range: -5.5838

Max Act: 3.8611. Min Act: -0.0000

Data Index: 1416692 (Python Code)

Max Activating Token Index: 86

Text #16

Max Range: 5.5838. Min Range: -5.5838

Max Act: 3.7612. Min Act: -0.0000

Data Index: 1580281 (Python Code)

Max Activating Token Index: 845

Text #17

Max Range: 5.5838. Min Range: -5.5838

Max Act: 3.7541. Min Act: -0.0000

Data Index: 1381830 (Python Code)

Max Activating Token Index: 283

Text #18

Max Range: 5.5838. Min Range: -5.5838

Max Act: 3.6006. Min Act: -0.0000

Data Index: 1597514 (Python Code)

Max Activating Token Index: 832

Text #19

Max Range: 5.5838. Min Range: -5.5838

Max Act: 3.7212. Min Act: -0.0000

Data Index: 1403675 (Python Code)

Max Activating Token Index: 724