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

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

Neuron 4471 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3826. Min Range: -2.3826

Max Act: 2.3826. Min Act: -0.0000

Data Index: 1430982 (Python Code)

Max Activating Token Index: 850

Text #1

Max Range: 2.3826. Min Range: -2.3826

Max Act: 2.2382. Min Act: -0.0000

Data Index: 1615636 (Python Code)

Max Activating Token Index: 547

Text #2

Max Range: 2.3826. Min Range: -2.3826

Max Act: 2.3435. Min Act: -0.0000

Data Index: 1549797 (Python Code)

Max Activating Token Index: 70

Text #3

Max Range: 2.3826. Min Range: -2.3826

Max Act: 2.0126. Min Act: -0.0000

Data Index: 1469301 (Python Code)

Max Activating Token Index: 563

Text #4

Max Range: 2.3826. Min Range: -2.3826

Max Act: 2.3297. Min Act: -0.0000

Data Index: 1588210 (Python Code)

Max Activating Token Index: 53

Text #5

Max Range: 2.3826. Min Range: -2.3826

Max Act: 2.3737. Min Act: -0.0000

Data Index: 1437398 (Python Code)

Max Activating Token Index: 863

Text #6

Max Range: 2.3826. Min Range: -2.3826

Max Act: 2.2390. Min Act: -0.0000

Data Index: 1575057 (Python Code)

Max Activating Token Index: 994

Text #7

Max Range: 2.3826. Min Range: -2.3826

Max Act: 2.0449. Min Act: -0.0000

Data Index: 1390886 (Python Code)

Max Activating Token Index: 699

Text #8

Max Range: 2.3826. Min Range: -2.3826

Max Act: 1.7572. Min Act: -0.0000

Data Index: 1438313 (Python Code)

Max Activating Token Index: 977

Text #9

Max Range: 2.3826. Min Range: -2.3826

Max Act: 2.0798. Min Act: -0.0000

Data Index: 1509345 (Python Code)

Max Activating Token Index: 906

Text #10

Max Range: 2.3826. Min Range: -2.3826

Max Act: 2.1621. Min Act: -0.0000

Data Index: 1478058 (Python Code)

Max Activating Token Index: 919

Text #11

Max Range: 2.3826. Min Range: -2.3826

Max Act: 2.2527. Min Act: -0.0000

Data Index: 1592892 (Python Code)

Max Activating Token Index: 911

Text #12

Max Range: 2.3826. Min Range: -2.3826

Max Act: 2.0814. Min Act: -0.0000

Data Index: 354139 (C4 (Web Text))

Max Activating Token Index: 940

Text #13

Max Range: 2.3826. Min Range: -2.3826

Max Act: 2.1506. Min Act: -0.0000

Data Index: 1412424 (Python Code)

Max Activating Token Index: 889

Text #14

Max Range: 2.3826. Min Range: -2.3826

Max Act: 2.0173. Min Act: -0.0000

Data Index: 1438392 (Python Code)

Max Activating Token Index: 630

Text #15

Max Range: 2.3826. Min Range: -2.3826

Max Act: 1.9230. Min Act: -0.0000

Data Index: 1237709 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 2.3826. Min Range: -2.3826

Max Act: 1.7582. Min Act: -0.0000

Data Index: 1641070 (Python Code)

Max Activating Token Index: 929

Text #17

Max Range: 2.3826. Min Range: -2.3826

Max Act: 1.8657. Min Act: -0.0000

Data Index: 1426584 (Python Code)

Max Activating Token Index: 930

Text #18

Max Range: 2.3826. Min Range: -2.3826

Max Act: 1.9626. Min Act: -0.0000

Data Index: 1586264 (Python Code)

Max Activating Token Index: 905

Text #19

Max Range: 2.3826. Min Range: -2.3826

Max Act: 1.8363. Min Act: -0.0000

Data Index: 1536987 (Python Code)

Max Activating Token Index: 846