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

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

Neuron 3908 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4269. Min Range: -1.4269

Max Act: 1.4269. Min Act: -0.0000

Data Index: 127595 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 1.4269. Min Range: -1.4269

Max Act: 1.3724. Min Act: -0.0000

Data Index: 1244231 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 1.4269. Min Range: -1.4269

Max Act: 1.3193. Min Act: -0.0000

Data Index: 505418 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 1.4269. Min Range: -1.4269

Max Act: 1.1853. Min Act: -0.0000

Data Index: 913026 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 1.4269. Min Range: -1.4269

Max Act: 1.1016. Min Act: -0.0000

Data Index: 996115 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 1.4269. Min Range: -1.4269

Max Act: 1.1333. Min Act: -0.0000

Data Index: 1086264 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 1.4269. Min Range: -1.4269

Max Act: 1.1736. Min Act: -0.0000

Data Index: 41199 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 1.4269. Min Range: -1.4269

Max Act: 1.2255. Min Act: -0.0000

Data Index: 1215543 (C4 (Web Text))

Max Activating Token Index: 794

Text #8

Max Range: 1.4269. Min Range: -1.4269

Max Act: 1.2209. Min Act: -0.0000

Data Index: 880127 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 1.4269. Min Range: -1.4269

Max Act: 1.0499. Min Act: -0.0000

Data Index: 1354480 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 1.4269. Min Range: -1.4269

Max Act: 1.1568. Min Act: -0.0000

Data Index: 845245 (C4 (Web Text))

Max Activating Token Index: 528

Text #11

Max Range: 1.4269. Min Range: -1.4269

Max Act: 1.0541. Min Act: -0.0000

Data Index: 792538 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 1.4269. Min Range: -1.4269

Max Act: 1.1254. Min Act: -0.0000

Data Index: 532706 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 1.4269. Min Range: -1.4269

Max Act: 1.0915. Min Act: -0.0000

Data Index: 1148311 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 1.4269. Min Range: -1.4269

Max Act: 1.0848. Min Act: -0.0000

Data Index: 781462 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 1.4269. Min Range: -1.4269

Max Act: 1.0696. Min Act: -0.0000

Data Index: 1101252 (C4 (Web Text))

Max Activating Token Index: 299

Text #16

Max Range: 1.4269. Min Range: -1.4269

Max Act: 0.8756. Min Act: -0.0000

Data Index: 388267 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 1.4269. Min Range: -1.4269

Max Act: 1.0935. Min Act: -0.0000

Data Index: 661257 (C4 (Web Text))

Max Activating Token Index: 211

Text #18

Max Range: 1.4269. Min Range: -1.4269

Max Act: 1.0220. Min Act: -0.0000

Data Index: 703228 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 1.4269. Min Range: -1.4269

Max Act: 0.8765. Min Act: -0.0000

Data Index: 602133 (C4 (Web Text))

Max Activating Token Index: 227