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

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

Neuron 3764 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: 5.5860. Min Range: -5.5860

Max Act: 5.5860. Min Act: -0.0000

Data Index: 1406921 (Python Code)

Max Activating Token Index: 816

Text #1

Max Range: 5.5860. Min Range: -5.5860

Max Act: 5.5750. Min Act: -0.0000

Data Index: 1436634 (Python Code)

Max Activating Token Index: 911

Text #2

Max Range: 5.5860. Min Range: -5.5860

Max Act: 5.2861. Min Act: -0.0000

Data Index: 1537863 (Python Code)

Max Activating Token Index: 577

Text #3

Max Range: 5.5860. Min Range: -5.5860

Max Act: 5.1050. Min Act: -0.0000

Data Index: 1461487 (Python Code)

Max Activating Token Index: 390

Text #4

Max Range: 5.5860. Min Range: -5.5860

Max Act: 5.2812. Min Act: -0.0000

Data Index: 1608055 (Python Code)

Max Activating Token Index: 529

Text #5

Max Range: 5.5860. Min Range: -5.5860

Max Act: 5.4607. Min Act: -0.0000

Data Index: 1367306 (Python Code)

Max Activating Token Index: 659

Text #6

Max Range: 5.5860. Min Range: -5.5860

Max Act: 4.7798. Min Act: -0.0000

Data Index: 1538542 (Python Code)

Max Activating Token Index: 659

Text #7

Max Range: 5.5860. Min Range: -5.5860

Max Act: 4.7420. Min Act: -0.0000

Data Index: 1363261 (Python Code)

Max Activating Token Index: 82

Text #8

Max Range: 5.5860. Min Range: -5.5860

Max Act: 4.6309. Min Act: -0.0000

Data Index: 1642951 (Python Code)

Max Activating Token Index: 622

Text #9

Max Range: 5.5860. Min Range: -5.5860

Max Act: 4.7685. Min Act: -0.0000

Data Index: 1633706 (Python Code)

Max Activating Token Index: 102

Text #10

Max Range: 5.5860. Min Range: -5.5860

Max Act: 4.1273. Min Act: -0.0000

Data Index: 1451267 (Python Code)

Max Activating Token Index: 712

Text #11

Max Range: 5.5860. Min Range: -5.5860

Max Act: 4.2351. Min Act: -0.0000

Data Index: 1615731 (Python Code)

Max Activating Token Index: 967

Text #12

Max Range: 5.5860. Min Range: -5.5860

Max Act: 3.7917. Min Act: -0.0000

Data Index: 1380560 (Python Code)

Max Activating Token Index: 645

Text #13

Max Range: 5.5860. Min Range: -5.5860

Max Act: 3.9888. Min Act: -0.0000

Data Index: 1633849 (Python Code)

Max Activating Token Index: 238

Text #14

Max Range: 5.5860. Min Range: -5.5860

Max Act: 3.6469. Min Act: -0.0000

Data Index: 1549534 (Python Code)

Max Activating Token Index: 144

Text #15

Max Range: 5.5860. Min Range: -5.5860

Max Act: 3.7816. Min Act: -0.0000

Data Index: 1611607 (Python Code)

Max Activating Token Index: 305

Text #16

Max Range: 5.5860. Min Range: -5.5860

Max Act: 3.9278. Min Act: -0.0000

Data Index: 1632748 (Python Code)

Max Activating Token Index: 13

Text #17

Max Range: 5.5860. Min Range: -5.5860

Max Act: 3.7226. Min Act: -0.0000

Data Index: 1551935 (Python Code)

Max Activating Token Index: 973

Text #18

Max Range: 5.5860. Min Range: -5.5860

Max Act: 3.3856. Min Act: -0.0000

Data Index: 1609365 (Python Code)

Max Activating Token Index: 1001

Text #19

Max Range: 5.5860. Min Range: -5.5860

Max Act: 3.8598. Min Act: -0.0000

Data Index: 1656717 (Python Code)

Max Activating Token Index: 1000