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

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

Neuron 3904 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.1161. Min Act: -0.0000

Data Index: 136592 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0867. Min Act: -0.0000

Data Index: 349349 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0851. Min Act: -0.0000

Data Index: 571764 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0847. Min Act: -0.0000

Data Index: 536414 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0755. Min Act: -0.0000

Data Index: 497953 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0742. Min Act: -0.0000

Data Index: 1482552 (Python Code)

Max Activating Token Index: 901

Text #6

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0756. Min Act: -0.0000

Data Index: 1146550 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0814. Min Act: -0.0000

Data Index: 856484 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0806. Min Act: -0.0000

Data Index: 1103167 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0730. Min Act: -0.0000

Data Index: 466387 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0752. Min Act: -0.0000

Data Index: 1560648 (Python Code)

Max Activating Token Index: 807

Text #11

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0714. Min Act: -0.0000

Data Index: 1404728 (Python Code)

Max Activating Token Index: 678

Text #12

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0745. Min Act: -0.0000

Data Index: 342997 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0734. Min Act: -0.0000

Data Index: 681081 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0733. Min Act: -0.0000

Data Index: 1530576 (Python Code)

Max Activating Token Index: 681

Text #15

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0733. Min Act: -0.0000

Data Index: 747802 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0768. Min Act: -0.0000

Data Index: 48793 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0609. Min Act: -0.0000

Data Index: 790988 (C4 (Web Text))

Max Activating Token Index: 131

Text #18

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0697. Min Act: -0.0000

Data Index: 656375 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0698. Min Act: -0.0000

Data Index: 638535 (C4 (Web Text))

Max Activating Token Index: 533