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

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

Neuron 1970 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6426. Min Range: -1.6426

Max Act: 1.6426. Min Act: -0.0000

Data Index: 447679 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 1.6426. Min Range: -1.6426

Max Act: 1.6302. Min Act: -0.0000

Data Index: 199894 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 1.6426. Min Range: -1.6426

Max Act: 1.4379. Min Act: -0.0000

Data Index: 844644 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 1.6426. Min Range: -1.6426

Max Act: 1.5088. Min Act: -0.0000

Data Index: 988736 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 1.6426. Min Range: -1.6426

Max Act: 1.2773. Min Act: -0.0000

Data Index: 1265436 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 1.6426. Min Range: -1.6426

Max Act: 1.2074. Min Act: -0.0000

Data Index: 474718 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 1.6426. Min Range: -1.6426

Max Act: 1.2852. Min Act: -0.0000

Data Index: 1022859 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 1.6426. Min Range: -1.6426

Max Act: 1.1789. Min Act: -0.0000

Data Index: 483610 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 1.6426. Min Range: -1.6426

Max Act: 1.2466. Min Act: -0.0000

Data Index: 956777 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 1.6426. Min Range: -1.6426

Max Act: 1.1745. Min Act: -0.0000

Data Index: 844354 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 1.6426. Min Range: -1.6426

Max Act: 1.1429. Min Act: -0.0000

Data Index: 875097 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 1.6426. Min Range: -1.6426

Max Act: 1.2775. Min Act: -0.0000

Data Index: 609543 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 1.6426. Min Range: -1.6426

Max Act: 1.2813. Min Act: -0.0000

Data Index: 719950 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 1.6426. Min Range: -1.6426

Max Act: 1.2002. Min Act: -0.0000

Data Index: 650074 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 1.6426. Min Range: -1.6426

Max Act: 1.2816. Min Act: -0.0000

Data Index: 800052 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 1.6426. Min Range: -1.6426

Max Act: 1.1911. Min Act: -0.0000

Data Index: 780776 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 1.6426. Min Range: -1.6426

Max Act: 1.0490. Min Act: -0.0000

Data Index: 1143235 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 1.6426. Min Range: -1.6426

Max Act: 1.1751. Min Act: -0.0000

Data Index: 40799 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 1.6426. Min Range: -1.6426

Max Act: 1.0951. Min Act: -0.0000

Data Index: 23697 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 1.6426. Min Range: -1.6426

Max Act: 1.0200. Min Act: -0.0000

Data Index: 8274 (C4 (Web Text))

Max Activating Token Index: 175