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

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

Neuron 4727 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9794. Min Range: -2.9794

Max Act: 2.9794. Min Act: -0.0000

Data Index: 1468348 (Python Code)

Max Activating Token Index: 682

Text #1

Max Range: 2.9794. Min Range: -2.9794

Max Act: 2.2861. Min Act: -0.0000

Data Index: 597938 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 2.9794. Min Range: -2.9794

Max Act: 2.0191. Min Act: -0.0000

Data Index: 931791 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 2.9794. Min Range: -2.9794

Max Act: 2.2209. Min Act: -0.0000

Data Index: 396931 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 2.9794. Min Range: -2.9794

Max Act: 2.1800. Min Act: -0.0000

Data Index: 877564 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 2.9794. Min Range: -2.9794

Max Act: 1.9979. Min Act: -0.0000

Data Index: 52814 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 2.9794. Min Range: -2.9794

Max Act: 1.8857. Min Act: -0.0000

Data Index: 645098 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 2.9794. Min Range: -2.9794

Max Act: 1.6896. Min Act: -0.0000

Data Index: 195632 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 2.9794. Min Range: -2.9794

Max Act: 1.9080. Min Act: -0.0000

Data Index: 298971 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 2.9794. Min Range: -2.9794

Max Act: 1.8940. Min Act: -0.0000

Data Index: 993885 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 2.9794. Min Range: -2.9794

Max Act: 1.9104. Min Act: -0.0000

Data Index: 381680 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 2.9794. Min Range: -2.9794

Max Act: 1.7911. Min Act: -0.0000

Data Index: 1433360 (Python Code)

Max Activating Token Index: 474

Text #12

Max Range: 2.9794. Min Range: -2.9794

Max Act: 1.8010. Min Act: -0.0000

Data Index: 609822 (C4 (Web Text))

Max Activating Token Index: 344

Text #13

Max Range: 2.9794. Min Range: -2.9794

Max Act: 1.6923. Min Act: -0.0000

Data Index: 246056 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 2.9794. Min Range: -2.9794

Max Act: 1.5825. Min Act: -0.0000

Data Index: 943127 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 2.9794. Min Range: -2.9794

Max Act: 1.7678. Min Act: -0.0000

Data Index: 595243 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 2.9794. Min Range: -2.9794

Max Act: 1.6988. Min Act: -0.0000

Data Index: 793431 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 2.9794. Min Range: -2.9794

Max Act: 1.6452. Min Act: -0.0000

Data Index: 1137549 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 2.9794. Min Range: -2.9794

Max Act: 1.5310. Min Act: -0.0000

Data Index: 476574 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 2.9794. Min Range: -2.9794

Max Act: 1.8010. Min Act: -0.0000

Data Index: 1231026 (C4 (Web Text))

Max Activating Token Index: 618