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

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

Neuron 6079 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1690. Min Range: -1.1690

Max Act: 1.1690. Min Act: -0.0001

Data Index: 76302 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 1.1690. Min Range: -1.1690

Max Act: 1.0271. Min Act: -0.0001

Data Index: 1267488 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 1.1690. Min Range: -1.1690

Max Act: 1.0783. Min Act: -0.0001

Data Index: 644547 (C4 (Web Text))

Max Activating Token Index: 766

Text #3

Max Range: 1.1690. Min Range: -1.1690

Max Act: 1.0543. Min Act: -0.0001

Data Index: 942755 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 1.1690. Min Range: -1.1690

Max Act: 1.0596. Min Act: -0.0001

Data Index: 146443 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 1.1690. Min Range: -1.1690

Max Act: 1.0479. Min Act: -0.0001

Data Index: 481329 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 1.1690. Min Range: -1.1690

Max Act: 0.8759. Min Act: -0.0000

Data Index: 541778 (C4 (Web Text))

Max Activating Token Index: 368

Text #7

Max Range: 1.1690. Min Range: -1.1690

Max Act: 0.8821. Min Act: -0.0001

Data Index: 992247 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 1.1690. Min Range: -1.1690

Max Act: 0.8165. Min Act: -0.0000

Data Index: 134834 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 1.1690. Min Range: -1.1690

Max Act: 0.8506. Min Act: -0.0000

Data Index: 764143 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 1.1690. Min Range: -1.1690

Max Act: 0.8851. Min Act: -0.0001

Data Index: 91766 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 1.1690. Min Range: -1.1690

Max Act: 0.8503. Min Act: -0.0000

Data Index: 805758 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 1.1690. Min Range: -1.1690

Max Act: 0.8793. Min Act: -0.0001

Data Index: 127928 (C4 (Web Text))

Max Activating Token Index: 376

Text #13

Max Range: 1.1690. Min Range: -1.1690

Max Act: 0.8688. Min Act: -0.0000

Data Index: 1439787 (Python Code)

Max Activating Token Index: 647

Text #14

Max Range: 1.1690. Min Range: -1.1690

Max Act: 0.8816. Min Act: -0.0000

Data Index: 826526 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 1.1690. Min Range: -1.1690

Max Act: 0.8105. Min Act: -0.0000

Data Index: 1162022 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 1.1690. Min Range: -1.1690

Max Act: 0.8284. Min Act: -0.0001

Data Index: 765377 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 1.1690. Min Range: -1.1690

Max Act: 0.9104. Min Act: -0.0000

Data Index: 83577 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 1.1690. Min Range: -1.1690

Max Act: 0.8794. Min Act: -0.0001

Data Index: 418974 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 1.1690. Min Range: -1.1690

Max Act: 0.8821. Min Act: -0.0001

Data Index: 1262326 (C4 (Web Text))

Max Activating Token Index: 5