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

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

Neuron 553 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.9754. Min Act: -0.0000

Data Index: 938559 (C4 (Web Text))

Max Activating Token Index: 622

Text #1

Max Range: 1.0794. Min Range: -1.0794

Max Act: 1.0794. Min Act: -0.0000

Data Index: 102165 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.8964. Min Act: -0.0000

Data Index: 1296566 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.8763. Min Act: -0.0000

Data Index: 1170612 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.6977. Min Act: -0.0000

Data Index: 17159 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.6913. Min Act: -0.0000

Data Index: 1495926 (Python Code)

Max Activating Token Index: 378

Text #6

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.7315. Min Act: -0.0000

Data Index: 1409221 (Python Code)

Max Activating Token Index: 553

Text #7

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.7491. Min Act: -0.0000

Data Index: 1654531 (Python Code)

Max Activating Token Index: 602

Text #8

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.6781. Min Act: -0.0000

Data Index: 1439530 (Python Code)

Max Activating Token Index: 847

Text #9

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.6982. Min Act: -0.0000

Data Index: 1566506 (Python Code)

Max Activating Token Index: 743

Text #10

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.7501. Min Act: -0.0000

Data Index: 118000 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.6933. Min Act: -0.0000

Data Index: 1381180 (Python Code)

Max Activating Token Index: 768

Text #12

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.6870. Min Act: -0.0000

Data Index: 1478036 (Python Code)

Max Activating Token Index: 419

Text #13

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.7023. Min Act: -0.0000

Data Index: 1382222 (Python Code)

Max Activating Token Index: 865

Text #14

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.7202. Min Act: -0.0000

Data Index: 1466812 (Python Code)

Max Activating Token Index: 509

Text #15

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.6734. Min Act: -0.0000

Data Index: 1510159 (Python Code)

Max Activating Token Index: 776

Text #16

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.7000. Min Act: -0.0000

Data Index: 1643001 (Python Code)

Max Activating Token Index: 878

Text #17

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.6297. Min Act: -0.0000

Data Index: 1452668 (Python Code)

Max Activating Token Index: 730

Text #18

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.6675. Min Act: -0.0000

Data Index: 1418792 (Python Code)

Max Activating Token Index: 592

Text #19

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.6624. Min Act: -0.0000

Data Index: 1580154 (Python Code)

Max Activating Token Index: 313