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

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

Neuron 3886 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: 0.1178. Min Range: -0.1178

Max Act: 0.1178. Min Act: -0.0000

Data Index: 627834 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0844. Min Act: -0.0000

Data Index: 1349737 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0865. Min Act: -0.0000

Data Index: 817446 (C4 (Web Text))

Max Activating Token Index: 377

Text #3

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0791. Min Act: -0.0000

Data Index: 896617 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0805. Min Act: -0.0000

Data Index: 267798 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0805. Min Act: -0.0000

Data Index: 1045505 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0785. Min Act: -0.0000

Data Index: 606687 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0758. Min Act: -0.0000

Data Index: 1237389 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0674. Min Act: -0.0000

Data Index: 927413 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0687. Min Act: -0.0001

Data Index: 1463927 (Python Code)

Max Activating Token Index: 572

Text #10

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0650. Min Act: -0.0000

Data Index: 699829 (C4 (Web Text))

Max Activating Token Index: 885

Text #11

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0759. Min Act: -0.0000

Data Index: 658882 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0759. Min Act: -0.0000

Data Index: 12414 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0696. Min Act: -0.0000

Data Index: 720551 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0746. Min Act: -0.0000

Data Index: 1175125 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0653. Min Act: -0.0000

Data Index: 684528 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0677. Min Act: -0.0000

Data Index: 901241 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0677. Min Act: -0.0001

Data Index: 1519441 (Python Code)

Max Activating Token Index: 522

Text #18

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0692. Min Act: -0.0000

Data Index: 124742 (C4 (Web Text))

Max Activating Token Index: 429

Text #19

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0600. Min Act: -0.0000

Data Index: 495742 (C4 (Web Text))

Max Activating Token Index: 909