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

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

Neuron 1272 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1160. Min Act: -0.0000

Data Index: 1097785 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0917. Min Act: -0.0000

Data Index: 787767 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0825. Min Act: -0.0000

Data Index: 592226 (C4 (Web Text))

Max Activating Token Index: 864

Text #3

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0767. Min Act: -0.0000

Data Index: 337497 (C4 (Web Text))

Max Activating Token Index: 644

Text #4

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0790. Min Act: -0.0000

Data Index: 985242 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0701. Min Act: -0.0000

Data Index: 567556 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0700. Min Act: -0.0000

Data Index: 485161 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0668. Min Act: -0.0000

Data Index: 23575 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0633. Min Act: -0.0000

Data Index: 661501 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0679. Min Act: -0.0000

Data Index: 466993 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0698. Min Act: -0.0000

Data Index: 1526398 (Python Code)

Max Activating Token Index: 26

Text #11

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0603. Min Act: -0.0000

Data Index: 1434232 (Python Code)

Max Activating Token Index: 424

Text #12

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0685. Min Act: -0.0000

Data Index: 1577574 (Python Code)

Max Activating Token Index: 34

Text #13

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0672. Min Act: -0.0000

Data Index: 1181659 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0678. Min Act: -0.0000

Data Index: 1153606 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0679. Min Act: -0.0000

Data Index: 1545023 (Python Code)

Max Activating Token Index: 100

Text #16

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0621. Min Act: -0.0000

Data Index: 489744 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0591. Min Act: -0.0000

Data Index: 1351054 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0604. Min Act: -0.0000

Data Index: 1561321 (Python Code)

Max Activating Token Index: 199

Text #19

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0642. Min Act: -0.0000

Data Index: 37183 (C4 (Web Text))

Max Activating Token Index: 935