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

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

Neuron 3308 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0537. Min Range: -1.0537

Max Act: 1.0537. Min Act: -0.0000

Data Index: 625796 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 1.0537. Min Range: -1.0537

Max Act: 0.9223. Min Act: -0.0000

Data Index: 504810 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 1.0537. Min Range: -1.0537

Max Act: 0.8873. Min Act: -0.0000

Data Index: 437756 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 1.0537. Min Range: -1.0537

Max Act: 0.8816. Min Act: -0.0000

Data Index: 157154 (C4 (Web Text))

Max Activating Token Index: 554

Text #4

Max Range: 1.0537. Min Range: -1.0537

Max Act: 0.8253. Min Act: -0.0000

Data Index: 718333 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 1.0537. Min Range: -1.0537

Max Act: 0.8380. Min Act: -0.0000

Data Index: 652892 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 1.0537. Min Range: -1.0537

Max Act: 0.7689. Min Act: -0.0000

Data Index: 388551 (C4 (Web Text))

Max Activating Token Index: 793

Text #7

Max Range: 1.0537. Min Range: -1.0537

Max Act: 0.7472. Min Act: -0.0000

Data Index: 811758 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 1.0537. Min Range: -1.0537

Max Act: 0.7625. Min Act: -0.0000

Data Index: 37550 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 1.0537. Min Range: -1.0537

Max Act: 0.7540. Min Act: 0.0000

Data Index: 1348198 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 1.0537. Min Range: -1.0537

Max Act: 0.7537. Min Act: -0.0000

Data Index: 131133 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 1.0537. Min Range: -1.0537

Max Act: 0.7459. Min Act: -0.0000

Data Index: 362067 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 1.0537. Min Range: -1.0537

Max Act: 0.7118. Min Act: -0.0000

Data Index: 608711 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 1.0537. Min Range: -1.0537

Max Act: 0.6626. Min Act: -0.0000

Data Index: 1142718 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 1.0537. Min Range: -1.0537

Max Act: 0.8674. Min Act: -0.0000

Data Index: 133760 (C4 (Web Text))

Max Activating Token Index: 677

Text #15

Max Range: 1.0537. Min Range: -1.0537

Max Act: 0.7379. Min Act: -0.0000

Data Index: 798704 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 1.0537. Min Range: -1.0537

Max Act: 0.6618. Min Act: -0.0000

Data Index: 258915 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 1.0537. Min Range: -1.0537

Max Act: 0.6782. Min Act: -0.0000

Data Index: 1220947 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 1.0537. Min Range: -1.0537

Max Act: 0.6957. Min Act: -0.0000

Data Index: 355157 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 1.0537. Min Range: -1.0537

Max Act: 0.6815. Min Act: -0.0000

Data Index: 975337 (C4 (Web Text))

Max Activating Token Index: 942