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

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

Neuron 2197 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: 1.7710. Min Range: -1.7710

Max Act: 1.7710. Min Act: -0.0000

Data Index: 1618870 (Python Code)

Max Activating Token Index: 821

Text #1

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.7002. Min Act: -0.0000

Data Index: 1447823 (Python Code)

Max Activating Token Index: 158

Text #2

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.6152. Min Act: -0.0000

Data Index: 1571540 (Python Code)

Max Activating Token Index: 286

Text #3

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.3075. Min Act: -0.0000

Data Index: 1638030 (Python Code)

Max Activating Token Index: 337

Text #4

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.3859. Min Act: -0.0000

Data Index: 1378017 (Python Code)

Max Activating Token Index: 94

Text #5

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.2866. Min Act: -0.0000

Data Index: 1415215 (Python Code)

Max Activating Token Index: 713

Text #6

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.3544. Min Act: -0.0000

Data Index: 1484786 (Python Code)

Max Activating Token Index: 831

Text #7

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.3454. Min Act: 0.0000

Data Index: 1620966 (Python Code)

Max Activating Token Index: 857

Text #8

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.2228. Min Act: -0.0000

Data Index: 1407297 (Python Code)

Max Activating Token Index: 961

Text #9

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.3894. Min Act: -0.0000

Data Index: 1578996 (Python Code)

Max Activating Token Index: 301

Text #10

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.3678. Min Act: -0.0000

Data Index: 1586107 (Python Code)

Max Activating Token Index: 238

Text #11

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.2823. Min Act: -0.0000

Data Index: 1392724 (Python Code)

Max Activating Token Index: 847

Text #12

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.3371. Min Act: -0.0000

Data Index: 1618783 (Python Code)

Max Activating Token Index: 711

Text #13

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.1664. Min Act: -0.0000

Data Index: 1502311 (Python Code)

Max Activating Token Index: 105

Text #14

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.1892. Min Act: 0.0001

Data Index: 1513513 (Python Code)

Max Activating Token Index: 949

Text #15

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.1720. Min Act: -0.0000

Data Index: 1536900 (Python Code)

Max Activating Token Index: 851

Text #16

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.1677. Min Act: -0.0000

Data Index: 1420776 (Python Code)

Max Activating Token Index: 991

Text #17

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.0394. Min Act: -0.0000

Data Index: 1584594 (Python Code)

Max Activating Token Index: 283

Text #18

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.1263. Min Act: -0.0000

Data Index: 1410655 (Python Code)

Max Activating Token Index: 771

Text #19

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.0444. Min Act: -0.0000

Data Index: 1644357 (Python Code)

Max Activating Token Index: 174