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

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

Neuron 2228 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.3504. Min Act: -0.0000

Data Index: 965288 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.3564. Min Act: -0.0000

Data Index: 1322905 (C4 (Web Text))

Max Activating Token Index: 442

Text #2

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.3757. Min Act: -0.0000

Data Index: 1200145 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.3635. Min Act: -0.0000

Data Index: 822874 (C4 (Web Text))

Max Activating Token Index: 533

Text #4

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.3106. Min Act: -0.0000

Data Index: 296558 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.3263. Min Act: -0.0000

Data Index: 657279 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.3239. Min Act: -0.0000

Data Index: 156764 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.3015. Min Act: -0.0000

Data Index: 1315771 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2985. Min Act: -0.0000

Data Index: 889372 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2850. Min Act: -0.0000

Data Index: 376550 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2649. Min Act: -0.0000

Data Index: 375515 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2602. Min Act: -0.0000

Data Index: 1100918 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2538. Min Act: -0.0000

Data Index: 336270 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2687. Min Act: -0.0000

Data Index: 901386 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2755. Min Act: -0.0000

Data Index: 508773 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2647. Min Act: -0.0000

Data Index: 729804 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2644. Min Act: -0.0000

Data Index: 834221 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2519. Min Act: -0.0000

Data Index: 459688 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2328. Min Act: -0.0000

Data Index: 700440 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2580. Min Act: -0.0000

Data Index: 579840 (C4 (Web Text))

Max Activating Token Index: 866