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

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

Neuron 2419 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.4539. Min Act: -0.0000

Data Index: 1060786 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.4151. Min Act: -0.0000

Data Index: 538269 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3989. Min Act: -0.0000

Data Index: 81266 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3684. Min Act: -0.0000

Data Index: 994131 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3297. Min Act: -0.0000

Data Index: 1509989 (Python Code)

Max Activating Token Index: 623

Text #5

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3218. Min Act: -0.0000

Data Index: 1499115 (Python Code)

Max Activating Token Index: 945

Text #6

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3297. Min Act: -0.0000

Data Index: 1020823 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3144. Min Act: -0.0000

Data Index: 1547399 (Python Code)

Max Activating Token Index: 169

Text #8

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3141. Min Act: -0.0000

Data Index: 1590314 (Python Code)

Max Activating Token Index: 977

Text #9

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3051. Min Act: -0.0000

Data Index: 1564444 (Python Code)

Max Activating Token Index: 727

Text #10

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.3306. Min Act: -0.0000

Data Index: 1516870 (Python Code)

Max Activating Token Index: 923

Text #11

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.2955. Min Act: -0.0000

Data Index: 931696 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.2865. Min Act: -0.0000

Data Index: 1368985 (Python Code)

Max Activating Token Index: 656

Text #13

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.2984. Min Act: -0.0000

Data Index: 1615184 (Python Code)

Max Activating Token Index: 997

Text #14

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.2762. Min Act: -0.0000

Data Index: 1438912 (Python Code)

Max Activating Token Index: 922

Text #15

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.2653. Min Act: -0.0000

Data Index: 629033 (C4 (Web Text))

Max Activating Token Index: 927

Text #16

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.2629. Min Act: -0.0000

Data Index: 571319 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.2615. Min Act: -0.0000

Data Index: 1463684 (Python Code)

Max Activating Token Index: 564

Text #18

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.2767. Min Act: -0.0000

Data Index: 1560555 (Python Code)

Max Activating Token Index: 779

Text #19

Max Range: 0.4539. Min Range: -0.4539

Max Act: 0.2668. Min Act: -0.0000

Data Index: 1538222 (Python Code)

Max Activating Token Index: 625