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

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

Neuron 1456 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9892. Min Range: -0.9892

Max Act: 0.9775. Min Act: -0.0000

Data Index: 1484646 (Python Code)

Max Activating Token Index: 381

Text #1

Max Range: 0.9892. Min Range: -0.9892

Max Act: 0.9434. Min Act: -0.0000

Data Index: 1362146 (Python Code)

Max Activating Token Index: 577

Text #2

Max Range: 0.9892. Min Range: -0.9892

Max Act: 0.8519. Min Act: -0.0000

Data Index: 1461774 (Python Code)

Max Activating Token Index: 762

Text #3

Max Range: 0.9892. Min Range: -0.9892

Max Act: 0.7656. Min Act: -0.0000

Data Index: 1555678 (Python Code)

Max Activating Token Index: 696

Text #4

Max Range: 0.9892. Min Range: -0.9892

Max Act: 0.9892. Min Act: -0.0000

Data Index: 1407507 (Python Code)

Max Activating Token Index: 771

Text #5

Max Range: 0.9892. Min Range: -0.9892

Max Act: 0.9476. Min Act: -0.0000

Data Index: 1433342 (Python Code)

Max Activating Token Index: 634

Text #6

Max Range: 0.9892. Min Range: -0.9892

Max Act: 0.9344. Min Act: -0.0000

Data Index: 1483073 (Python Code)

Max Activating Token Index: 788

Text #7

Max Range: 0.9892. Min Range: -0.9892

Max Act: 0.9519. Min Act: -0.0000

Data Index: 1455041 (Python Code)

Max Activating Token Index: 194

Text #8

Max Range: 0.9892. Min Range: -0.9892

Max Act: 0.8703. Min Act: -0.0000

Data Index: 1378305 (Python Code)

Max Activating Token Index: 325

Text #9

Max Range: 0.9892. Min Range: -0.9892

Max Act: 0.9082. Min Act: -0.0000

Data Index: 1611996 (Python Code)

Max Activating Token Index: 377

Text #10

Max Range: 0.9892. Min Range: -0.9892

Max Act: 0.9122. Min Act: -0.0000

Data Index: 1520266 (Python Code)

Max Activating Token Index: 781

Text #11

Max Range: 0.9892. Min Range: -0.9892

Max Act: 0.8427. Min Act: -0.0000

Data Index: 1446770 (Python Code)

Max Activating Token Index: 213

Text #12

Max Range: 0.9892. Min Range: -0.9892

Max Act: 0.9702. Min Act: -0.0000

Data Index: 1467997 (Python Code)

Max Activating Token Index: 613

Text #13

Max Range: 0.9892. Min Range: -0.9892

Max Act: 0.8801. Min Act: -0.0000

Data Index: 1641171 (Python Code)

Max Activating Token Index: 651

Text #14

Max Range: 0.9892. Min Range: -0.9892

Max Act: 0.8184. Min Act: -0.0000

Data Index: 1589272 (Python Code)

Max Activating Token Index: 63

Text #15

Max Range: 0.9892. Min Range: -0.9892

Max Act: 0.7982. Min Act: -0.0000

Data Index: 1523179 (Python Code)

Max Activating Token Index: 988

Text #16

Max Range: 0.9892. Min Range: -0.9892

Max Act: 0.6698. Min Act: -0.0000

Data Index: 366995 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 0.9892. Min Range: -0.9892

Max Act: 0.6321. Min Act: -0.0000

Data Index: 1007548 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.9892. Min Range: -0.9892

Max Act: 0.5611. Min Act: -0.0000

Data Index: 133884 (C4 (Web Text))

Max Activating Token Index: 813

Text #19

Max Range: 0.9892. Min Range: -0.9892

Max Act: 0.5222. Min Act: -0.0000

Data Index: 145586 (C4 (Web Text))

Max Activating Token Index: 851