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

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

Neuron 5548 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8903. Min Range: -4.8903

Max Act: 4.8903. Min Act: -0.0000

Data Index: 589686 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 4.8903. Min Range: -4.8903

Max Act: 4.0367. Min Act: -0.0000

Data Index: 312177 (C4 (Web Text))

Max Activating Token Index: 577

Text #2

Max Range: 4.8903. Min Range: -4.8903

Max Act: 3.7837. Min Act: -0.0000

Data Index: 3332 (C4 (Web Text))

Max Activating Token Index: 709

Text #3

Max Range: 4.8903. Min Range: -4.8903

Max Act: 3.2179. Min Act: -0.0000

Data Index: 827799 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 4.8903. Min Range: -4.8903

Max Act: 3.2012. Min Act: -0.0000

Data Index: 942002 (C4 (Web Text))

Max Activating Token Index: 346

Text #5

Max Range: 4.8903. Min Range: -4.8903

Max Act: 3.0303. Min Act: -0.0000

Data Index: 234442 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 4.8903. Min Range: -4.8903

Max Act: 3.1389. Min Act: -0.0000

Data Index: 810445 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 4.8903. Min Range: -4.8903

Max Act: 2.9100. Min Act: -0.0000

Data Index: 1356699 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 4.8903. Min Range: -4.8903

Max Act: 2.6750. Min Act: -0.0000

Data Index: 671456 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 4.8903. Min Range: -4.8903

Max Act: 2.8170. Min Act: -0.0000

Data Index: 272984 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 4.8903. Min Range: -4.8903

Max Act: 2.9571. Min Act: -0.0000

Data Index: 438456 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 4.8903. Min Range: -4.8903

Max Act: 2.7621. Min Act: -0.0000

Data Index: 430099 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 4.8903. Min Range: -4.8903

Max Act: 3.2417. Min Act: -0.0000

Data Index: 154718 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 4.8903. Min Range: -4.8903

Max Act: 2.7566. Min Act: -0.0000

Data Index: 1125966 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 4.8903. Min Range: -4.8903

Max Act: 2.9025. Min Act: -0.0000

Data Index: 82301 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 4.8903. Min Range: -4.8903

Max Act: 2.7005. Min Act: -0.0000

Data Index: 1274760 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 4.8903. Min Range: -4.8903

Max Act: 2.6658. Min Act: -0.0000

Data Index: 258865 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 4.8903. Min Range: -4.8903

Max Act: 2.5872. Min Act: -0.0000

Data Index: 1078281 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 4.8903. Min Range: -4.8903

Max Act: 2.6176. Min Act: -0.0000

Data Index: 721661 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 4.8903. Min Range: -4.8903

Max Act: 2.7487. Min Act: -0.0000

Data Index: 392921 (C4 (Web Text))

Max Activating Token Index: 866