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

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

Neuron 5991 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1584. Min Act: -0.0000

Data Index: 1104204 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1371. Min Act: -0.0000

Data Index: 8520 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1231. Min Act: -0.0000

Data Index: 717804 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.0999. Min Act: -0.0000

Data Index: 1415929 (Python Code)

Max Activating Token Index: 79

Text #4

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1093. Min Act: -0.0000

Data Index: 845513 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.0959. Min Act: -0.0000

Data Index: 427863 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1039. Min Act: -0.0000

Data Index: 1617676 (Python Code)

Max Activating Token Index: 32

Text #7

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.0995. Min Act: -0.0000

Data Index: 759814 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.0934. Min Act: -0.0000

Data Index: 5541 (C4 (Web Text))

Max Activating Token Index: 868

Text #9

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.0995. Min Act: -0.0000

Data Index: 249472 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.0917. Min Act: -0.0000

Data Index: 1378042 (Python Code)

Max Activating Token Index: 110

Text #11

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.0945. Min Act: -0.0000

Data Index: 362110 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.0868. Min Act: -0.0000

Data Index: 57631 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.0769. Min Act: -0.0000

Data Index: 1483087 (Python Code)

Max Activating Token Index: 205

Text #14

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.0930. Min Act: -0.0000

Data Index: 767519 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.0879. Min Act: -0.0000

Data Index: 561240 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.0893. Min Act: -0.0000

Data Index: 480016 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.0914. Min Act: -0.0000

Data Index: 681150 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.0928. Min Act: -0.0000

Data Index: 985534 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.0832. Min Act: -0.0000

Data Index: 1587926 (Python Code)

Max Activating Token Index: 803