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

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

Neuron 4556 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: 6.7757. Min Range: -6.7757

Max Act: 6.7757. Min Act: -0.0000

Data Index: 447449 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 6.7757. Min Range: -6.7757

Max Act: 5.8518. Min Act: -0.0000

Data Index: 779729 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 6.7757. Min Range: -6.7757

Max Act: 5.6748. Min Act: -0.0000

Data Index: 328816 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 6.7757. Min Range: -6.7757

Max Act: 5.8543. Min Act: -0.0000

Data Index: 164767 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 6.7757. Min Range: -6.7757

Max Act: 5.3100. Min Act: -0.0000

Data Index: 1252519 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 6.7757. Min Range: -6.7757

Max Act: 5.4724. Min Act: -0.0000

Data Index: 942949 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 6.7757. Min Range: -6.7757

Max Act: 5.0886. Min Act: -0.0000

Data Index: 899637 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 6.7757. Min Range: -6.7757

Max Act: 5.2822. Min Act: -0.0000

Data Index: 436880 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 6.7757. Min Range: -6.7757

Max Act: 4.9776. Min Act: -0.0000

Data Index: 1134295 (C4 (Web Text))

Max Activating Token Index: 803

Text #9

Max Range: 6.7757. Min Range: -6.7757

Max Act: 4.9747. Min Act: -0.0000

Data Index: 878893 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 6.7757. Min Range: -6.7757

Max Act: 5.0972. Min Act: -0.0000

Data Index: 957097 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 6.7757. Min Range: -6.7757

Max Act: 4.5786. Min Act: -0.0000

Data Index: 654566 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 6.7757. Min Range: -6.7757

Max Act: 5.0180. Min Act: -0.0000

Data Index: 1030001 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 6.7757. Min Range: -6.7757

Max Act: 4.9413. Min Act: -0.0000

Data Index: 339556 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 6.7757. Min Range: -6.7757

Max Act: 4.7858. Min Act: -0.0000

Data Index: 193922 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 6.7757. Min Range: -6.7757

Max Act: 4.9355. Min Act: -0.0000

Data Index: 1351297 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 6.7757. Min Range: -6.7757

Max Act: 4.8363. Min Act: -0.0000

Data Index: 1098871 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 6.7757. Min Range: -6.7757

Max Act: 4.8327. Min Act: -0.0000

Data Index: 81505 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 6.7757. Min Range: -6.7757

Max Act: 4.6064. Min Act: -0.0000

Data Index: 114 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 6.7757. Min Range: -6.7757

Max Act: 4.3750. Min Act: -0.0000

Data Index: 300253 (C4 (Web Text))

Max Activating Token Index: 929