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

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

Neuron 4489 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.3882. Min Act: -0.0000

Data Index: 1477655 (Python Code)

Max Activating Token Index: 145

Text #1

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.3379. Min Act: -0.0000

Data Index: 1611039 (Python Code)

Max Activating Token Index: 73

Text #2

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.2902. Min Act: -0.0001

Data Index: 1554843 (Python Code)

Max Activating Token Index: 782

Text #3

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.2626. Min Act: -0.0001

Data Index: 1617052 (Python Code)

Max Activating Token Index: 435

Text #4

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.2379. Min Act: -0.0001

Data Index: 1520758 (Python Code)

Max Activating Token Index: 9

Text #5

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.2252. Min Act: -0.0001

Data Index: 1394494 (Python Code)

Max Activating Token Index: 495

Text #6

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.2097. Min Act: -0.0000

Data Index: 1606895 (Python Code)

Max Activating Token Index: 763

Text #7

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.2004. Min Act: -0.0000

Data Index: 1436093 (Python Code)

Max Activating Token Index: 795

Text #8

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.2007. Min Act: -0.0000

Data Index: 1596858 (Python Code)

Max Activating Token Index: 812

Text #9

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.2018. Min Act: -0.0001

Data Index: 1581667 (Python Code)

Max Activating Token Index: 420

Text #10

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.1838. Min Act: -0.0001

Data Index: 1479341 (Python Code)

Max Activating Token Index: 621

Text #11

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.1841. Min Act: -0.0001

Data Index: 525106 (C4 (Web Text))

Max Activating Token Index: 736

Text #12

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.1711. Min Act: -0.0000

Data Index: 1380453 (Python Code)

Max Activating Token Index: 613

Text #13

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.1844. Min Act: -0.0001

Data Index: 1426810 (Python Code)

Max Activating Token Index: 817

Text #14

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.1605. Min Act: -0.0001

Data Index: 1286056 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.1686. Min Act: -0.0001

Data Index: 551100 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.1792. Min Act: -0.0001

Data Index: 1431595 (Python Code)

Max Activating Token Index: 762

Text #17

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.1668. Min Act: -0.0000

Data Index: 1541184 (Python Code)

Max Activating Token Index: 759

Text #18

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.1642. Min Act: -0.0000

Data Index: 1397405 (Python Code)

Max Activating Token Index: 388

Text #19

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.1533. Min Act: -0.0000

Data Index: 1538912 (Python Code)

Max Activating Token Index: 508