Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 566 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.6895. Min Act: -0.0000

Data Index: 453623 (C4 (Web Text))

Max Activating Token Index: 157

Text #1

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5974. Min Act: -0.0000

Data Index: 97446 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5883. Min Act: -0.0000

Data Index: 432468 (C4 (Web Text))

Max Activating Token Index: 449

Text #3

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5850. Min Act: -0.0000

Data Index: 987622 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5883. Min Act: -0.0000

Data Index: 884325 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5957. Min Act: -0.0000

Data Index: 492534 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5560. Min Act: -0.0000

Data Index: 560088 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5570. Min Act: -0.0000

Data Index: 1248872 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5683. Min Act: -0.0000

Data Index: 412637 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5420. Min Act: -0.0000

Data Index: 768601 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5646. Min Act: -0.0000

Data Index: 1307656 (C4 (Web Text))

Max Activating Token Index: 932

Text #11

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5218. Min Act: -0.0000

Data Index: 749997 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.4993. Min Act: -0.0000

Data Index: 1335650 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5338. Min Act: -0.0000

Data Index: 913369 (C4 (Web Text))

Max Activating Token Index: 991

Text #14

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5053. Min Act: -0.0000

Data Index: 697331 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5119. Min Act: -0.0000

Data Index: 664580 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.4832. Min Act: 0.0000

Data Index: 1251662 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.4719. Min Act: -0.0000

Data Index: 844223 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.4629. Min Act: -0.0000

Data Index: 557897 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.4462. Min Act: -0.0000

Data Index: 621981 (C4 (Web Text))

Max Activating Token Index: 156