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

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

Neuron 3278 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: 2.3633. Min Range: -2.3633

Max Act: 2.3160. Min Act: -0.0000

Data Index: 1492571 (Python Code)

Max Activating Token Index: 485

Text #1

Max Range: 2.3633. Min Range: -2.3633

Max Act: 2.3633. Min Act: -0.0000

Data Index: 1384185 (Python Code)

Max Activating Token Index: 79

Text #2

Max Range: 2.3633. Min Range: -2.3633

Max Act: 2.1681. Min Act: -0.0000

Data Index: 1527947 (Python Code)

Max Activating Token Index: 22

Text #3

Max Range: 2.3633. Min Range: -2.3633

Max Act: 2.0576. Min Act: -0.0000

Data Index: 1484863 (Python Code)

Max Activating Token Index: 582

Text #4

Max Range: 2.3633. Min Range: -2.3633

Max Act: 2.2338. Min Act: -0.0000

Data Index: 399566 (C4 (Web Text))

Max Activating Token Index: 764

Text #5

Max Range: 2.3633. Min Range: -2.3633

Max Act: 2.1196. Min Act: -0.0000

Data Index: 1376667 (Python Code)

Max Activating Token Index: 16

Text #6

Max Range: 2.3633. Min Range: -2.3633

Max Act: 2.0995. Min Act: -0.0000

Data Index: 1606658 (Python Code)

Max Activating Token Index: 114

Text #7

Max Range: 2.3633. Min Range: -2.3633

Max Act: 1.9685. Min Act: -0.0000

Data Index: 1433503 (Python Code)

Max Activating Token Index: 525

Text #8

Max Range: 2.3633. Min Range: -2.3633

Max Act: 2.1321. Min Act: -0.0000

Data Index: 1635028 (Python Code)

Max Activating Token Index: 19

Text #9

Max Range: 2.3633. Min Range: -2.3633

Max Act: 2.0141. Min Act: -0.0000

Data Index: 1362101 (Python Code)

Max Activating Token Index: 917

Text #10

Max Range: 2.3633. Min Range: -2.3633

Max Act: 2.1217. Min Act: -0.0000

Data Index: 1440910 (Python Code)

Max Activating Token Index: 704

Text #11

Max Range: 2.3633. Min Range: -2.3633

Max Act: 2.0270. Min Act: -0.0000

Data Index: 1537739 (Python Code)

Max Activating Token Index: 1012

Text #12

Max Range: 2.3633. Min Range: -2.3633

Max Act: 1.9861. Min Act: -0.0000

Data Index: 1480066 (Python Code)

Max Activating Token Index: 502

Text #13

Max Range: 2.3633. Min Range: -2.3633

Max Act: 1.8813. Min Act: -0.0000

Data Index: 1394749 (Python Code)

Max Activating Token Index: 676

Text #14

Max Range: 2.3633. Min Range: -2.3633

Max Act: 2.0885. Min Act: -0.0000

Data Index: 1445363 (Python Code)

Max Activating Token Index: 114

Text #15

Max Range: 2.3633. Min Range: -2.3633

Max Act: 1.9297. Min Act: -0.0000

Data Index: 1645595 (Python Code)

Max Activating Token Index: 675

Text #16

Max Range: 2.3633. Min Range: -2.3633

Max Act: 1.8229. Min Act: -0.0000

Data Index: 1624595 (Python Code)

Max Activating Token Index: 9

Text #17

Max Range: 2.3633. Min Range: -2.3633

Max Act: 1.8060. Min Act: -0.0000

Data Index: 1477838 (Python Code)

Max Activating Token Index: 6

Text #18

Max Range: 2.3633. Min Range: -2.3633

Max Act: 2.0133. Min Act: -0.0000

Data Index: 1631686 (Python Code)

Max Activating Token Index: 981

Text #19

Max Range: 2.3633. Min Range: -2.3633

Max Act: 1.8055. Min Act: -0.0000

Data Index: 1610501 (Python Code)

Max Activating Token Index: 370