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

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

Neuron 2600 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: 1.2211. Min Range: -1.2211

Max Act: 1.2211. Min Act: -0.0000

Data Index: 801306 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 1.2211. Min Range: -1.2211

Max Act: 1.1833. Min Act: -0.0000

Data Index: 28066 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 1.2211. Min Range: -1.2211

Max Act: 1.1720. Min Act: -0.0000

Data Index: 148973 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 1.2211. Min Range: -1.2211

Max Act: 1.1730. Min Act: -0.0000

Data Index: 1233481 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 1.2211. Min Range: -1.2211

Max Act: 1.1832. Min Act: -0.0000

Data Index: 677416 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 1.2211. Min Range: -1.2211

Max Act: 1.1735. Min Act: -0.0000

Data Index: 537603 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 1.2211. Min Range: -1.2211

Max Act: 1.0812. Min Act: -0.0000

Data Index: 1165026 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 1.2211. Min Range: -1.2211

Max Act: 1.1468. Min Act: -0.0000

Data Index: 1000270 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 1.2211. Min Range: -1.2211

Max Act: 1.1491. Min Act: 0.0000

Data Index: 1079774 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 1.2211. Min Range: -1.2211

Max Act: 1.0824. Min Act: -0.0000

Data Index: 800761 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 1.2211. Min Range: -1.2211

Max Act: 1.0900. Min Act: -0.0000

Data Index: 1315105 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 1.2211. Min Range: -1.2211

Max Act: 1.0494. Min Act: -0.0000

Data Index: 671818 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 1.2211. Min Range: -1.2211

Max Act: 1.0458. Min Act: -0.0000

Data Index: 232758 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 1.2211. Min Range: -1.2211

Max Act: 1.0215. Min Act: -0.0000

Data Index: 42935 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 1.2211. Min Range: -1.2211

Max Act: 1.0337. Min Act: 0.0001

Data Index: 835487 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 1.2211. Min Range: -1.2211

Max Act: 1.0924. Min Act: -0.0000

Data Index: 564449 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 1.2211. Min Range: -1.2211

Max Act: 1.0336. Min Act: -0.0000

Data Index: 562364 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 1.2211. Min Range: -1.2211

Max Act: 0.9640. Min Act: -0.0000

Data Index: 73894 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 1.2211. Min Range: -1.2211

Max Act: 1.0103. Min Act: 0.0001

Data Index: 455928 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 1.2211. Min Range: -1.2211

Max Act: 1.0014. Min Act: 0.0000

Data Index: 1211199 (C4 (Web Text))

Max Activating Token Index: 154