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

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

Neuron 652 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: 0.2912. Min Range: -0.2912

Max Act: 0.2912. Min Act: -0.0000

Data Index: 362408 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2526. Min Act: -0.0000

Data Index: 717392 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.2311. Min Act: -0.0000

Data Index: 1085928 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.1986. Min Act: -0.0000

Data Index: 1074620 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.1520. Min Act: -0.0000

Data Index: 2871 (C4 (Web Text))

Max Activating Token Index: 212

Text #5

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.1753. Min Act: -0.0000

Data Index: 307709 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.1732. Min Act: -0.0000

Data Index: 275901 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.1608. Min Act: -0.0000

Data Index: 153443 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.1636. Min Act: -0.0000

Data Index: 57577 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.1508. Min Act: -0.0000

Data Index: 51982 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.1563. Min Act: -0.0000

Data Index: 1081626 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.1556. Min Act: -0.0000

Data Index: 946504 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.1667. Min Act: -0.0000

Data Index: 1236619 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.1394. Min Act: -0.0000

Data Index: 761163 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.1603. Min Act: -0.0000

Data Index: 406041 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.1492. Min Act: -0.0000

Data Index: 211741 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.1528. Min Act: -0.0000

Data Index: 233466 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.1574. Min Act: -0.0000

Data Index: 11041 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.1443. Min Act: -0.0000

Data Index: 1120856 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 0.2912. Min Range: -0.2912

Max Act: 0.1398. Min Act: -0.0000

Data Index: 442932 (C4 (Web Text))

Max Activating Token Index: 235