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

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

Neuron 2827 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3706. Min Range: -1.3706

Max Act: 1.2037. Min Act: -0.0000

Data Index: 1316442 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 1.3706. Min Range: -1.3706

Max Act: 1.2045. Min Act: -0.0000

Data Index: 447208 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 1.3706. Min Range: -1.3706

Max Act: 1.1579. Min Act: -0.0000

Data Index: 1190649 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 1.3706. Min Range: -1.3706

Max Act: 1.1470. Min Act: -0.0000

Data Index: 1191642 (C4 (Web Text))

Max Activating Token Index: 559

Text #4

Max Range: 1.3706. Min Range: -1.3706

Max Act: 1.3706. Min Act: -0.0000

Data Index: 34134 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 1.3706. Min Range: -1.3706

Max Act: 1.1819. Min Act: -0.0000

Data Index: 514220 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 1.3706. Min Range: -1.3706

Max Act: 1.0827. Min Act: -0.0000

Data Index: 678894 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 1.3706. Min Range: -1.3706

Max Act: 1.0838. Min Act: -0.0000

Data Index: 374517 (C4 (Web Text))

Max Activating Token Index: 320

Text #8

Max Range: 1.3706. Min Range: -1.3706

Max Act: 1.0447. Min Act: -0.0000

Data Index: 1474062 (Python Code)

Max Activating Token Index: 354

Text #9

Max Range: 1.3706. Min Range: -1.3706

Max Act: 1.0284. Min Act: -0.0000

Data Index: 517316 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 1.3706. Min Range: -1.3706

Max Act: 0.9987. Min Act: -0.0000

Data Index: 357770 (C4 (Web Text))

Max Activating Token Index: 529

Text #11

Max Range: 1.3706. Min Range: -1.3706

Max Act: 0.9999. Min Act: -0.0000

Data Index: 788479 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 1.3706. Min Range: -1.3706

Max Act: 1.0185. Min Act: -0.0000

Data Index: 936066 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 1.3706. Min Range: -1.3706

Max Act: 1.0540. Min Act: -0.0000

Data Index: 44038 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 1.3706. Min Range: -1.3706

Max Act: 1.0415. Min Act: -0.0000

Data Index: 204721 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 1.3706. Min Range: -1.3706

Max Act: 0.9644. Min Act: -0.0000

Data Index: 184296 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 1.3706. Min Range: -1.3706

Max Act: 1.0441. Min Act: -0.0000

Data Index: 670619 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 1.3706. Min Range: -1.3706

Max Act: 0.9516. Min Act: -0.0000

Data Index: 1443815 (Python Code)

Max Activating Token Index: 943

Text #18

Max Range: 1.3706. Min Range: -1.3706

Max Act: 0.9805. Min Act: -0.0000

Data Index: 19961 (C4 (Web Text))

Max Activating Token Index: 81

Text #19

Max Range: 1.3706. Min Range: -1.3706

Max Act: 0.9220. Min Act: -0.0000

Data Index: 1346263 (C4 (Web Text))

Max Activating Token Index: 224