Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3798 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2427. Min Range: -0.2427

Max Act: 0.2427. Min Act: -0.0000

Data Index: 783441 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 0.2427. Min Range: -0.2427

Max Act: 0.1998. Min Act: -0.0000

Data Index: 867904 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 0.2427. Min Range: -0.2427

Max Act: 0.2016. Min Act: -0.0000

Data Index: 37726 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 0.2427. Min Range: -0.2427

Max Act: 0.2217. Min Act: -0.0000

Data Index: 577465 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 0.2427. Min Range: -0.2427

Max Act: 0.2003. Min Act: -0.0000

Data Index: 987244 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 0.2427. Min Range: -0.2427

Max Act: 0.2014. Min Act: -0.0000

Data Index: 1461921 (Python Code)

Max Activating Token Index: 940

Text #6

Max Range: 0.2427. Min Range: -0.2427

Max Act: 0.1881. Min Act: -0.0000

Data Index: 371028 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 0.2427. Min Range: -0.2427

Max Act: 0.1896. Min Act: -0.0000

Data Index: 298592 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 0.2427. Min Range: -0.2427

Max Act: 0.1818. Min Act: -0.0000

Data Index: 1006846 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 0.2427. Min Range: -0.2427

Max Act: 0.1705. Min Act: -0.0000

Data Index: 321070 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 0.2427. Min Range: -0.2427

Max Act: 0.1786. Min Act: -0.0000

Data Index: 493851 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 0.2427. Min Range: -0.2427

Max Act: 0.1609. Min Act: -0.0000

Data Index: 1628882 (Python Code)

Max Activating Token Index: 571

Text #12

Max Range: 0.2427. Min Range: -0.2427

Max Act: 0.1571. Min Act: -0.0000

Data Index: 1428957 (Python Code)

Max Activating Token Index: 132

Text #13

Max Range: 0.2427. Min Range: -0.2427

Max Act: 0.1670. Min Act: -0.0000

Data Index: 471222 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 0.2427. Min Range: -0.2427

Max Act: 0.1825. Min Act: -0.0000

Data Index: 1439149 (Python Code)

Max Activating Token Index: 132

Text #15

Max Range: 0.2427. Min Range: -0.2427

Max Act: 0.1689. Min Act: -0.0000

Data Index: 1509405 (Python Code)

Max Activating Token Index: 31

Text #16

Max Range: 0.2427. Min Range: -0.2427

Max Act: 0.1746. Min Act: -0.0000

Data Index: 1569233 (Python Code)

Max Activating Token Index: 893

Text #17

Max Range: 0.2427. Min Range: -0.2427

Max Act: 0.1562. Min Act: -0.0000

Data Index: 403993 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 0.2427. Min Range: -0.2427

Max Act: 0.1611. Min Act: -0.0000

Data Index: 1471984 (Python Code)

Max Activating Token Index: 15

Text #19

Max Range: 0.2427. Min Range: -0.2427

Max Act: 0.1464. Min Act: -0.0000

Data Index: 321518 (C4 (Web Text))

Max Activating Token Index: 247