Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2990 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1264. Min Act: -0.0001

Data Index: 570445 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1152. Min Act: -0.0001

Data Index: 969105 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0853. Min Act: -0.0001

Data Index: 961003 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0883. Min Act: -0.0001

Data Index: 670641 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0823. Min Act: -0.0001

Data Index: 17343 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0849. Min Act: -0.0001

Data Index: 250934 (C4 (Web Text))

Max Activating Token Index: 512

Text #6

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0828. Min Act: -0.0001

Data Index: 727290 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0836. Min Act: -0.0001

Data Index: 346747 (C4 (Web Text))

Max Activating Token Index: 394

Text #8

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0866. Min Act: -0.0001

Data Index: 52989 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0805. Min Act: -0.0001

Data Index: 613467 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0736. Min Act: -0.0001

Data Index: 122394 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0781. Min Act: -0.0001

Data Index: 971989 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0770. Min Act: -0.0001

Data Index: 503808 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0767. Min Act: -0.0001

Data Index: 709357 (C4 (Web Text))

Max Activating Token Index: 433

Text #14

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0698. Min Act: -0.0001

Data Index: 909714 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0756. Min Act: -0.0001

Data Index: 438627 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0786. Min Act: -0.0001

Data Index: 314332 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0774. Min Act: -0.0001

Data Index: 418099 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0686. Min Act: -0.0001

Data Index: 883593 (C4 (Web Text))

Max Activating Token Index: 392

Text #19

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0691. Min Act: -0.0001

Data Index: 909002 (C4 (Web Text))

Max Activating Token Index: 847