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

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

Neuron 2822 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.9364. Min Range: -6.9364

Max Act: 6.9364. Min Act: -0.0000

Data Index: 168514 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 6.9364. Min Range: -6.9364

Max Act: 6.6774. Min Act: -0.0000

Data Index: 1049359 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 6.9364. Min Range: -6.9364

Max Act: 5.3562. Min Act: -0.0000

Data Index: 276426 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 6.9364. Min Range: -6.9364

Max Act: 5.6520. Min Act: -0.0000

Data Index: 396392 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 6.9364. Min Range: -6.9364

Max Act: 4.8551. Min Act: -0.0000

Data Index: 446417 (C4 (Web Text))

Max Activating Token Index: 942

Text #5

Max Range: 6.9364. Min Range: -6.9364

Max Act: 4.5611. Min Act: -0.0000

Data Index: 1088903 (C4 (Web Text))

Max Activating Token Index: 734

Text #6

Max Range: 6.9364. Min Range: -6.9364

Max Act: 4.7188. Min Act: -0.0000

Data Index: 925823 (C4 (Web Text))

Max Activating Token Index: 376

Text #7

Max Range: 6.9364. Min Range: -6.9364

Max Act: 4.1726. Min Act: -0.0000

Data Index: 1246858 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 6.9364. Min Range: -6.9364

Max Act: 3.9691. Min Act: -0.0000

Data Index: 46093 (C4 (Web Text))

Max Activating Token Index: 795

Text #9

Max Range: 6.9364. Min Range: -6.9364

Max Act: 4.4148. Min Act: -0.0000

Data Index: 598902 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 6.9364. Min Range: -6.9364

Max Act: 4.2809. Min Act: -0.0000

Data Index: 1409827 (Python Code)

Max Activating Token Index: 217

Text #11

Max Range: 6.9364. Min Range: -6.9364

Max Act: 3.8273. Min Act: -0.0000

Data Index: 1044599 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 6.9364. Min Range: -6.9364

Max Act: 4.9010. Min Act: -0.0000

Data Index: 438838 (C4 (Web Text))

Max Activating Token Index: 339

Text #13

Max Range: 6.9364. Min Range: -6.9364

Max Act: 3.9692. Min Act: -0.0000

Data Index: 1462739 (Python Code)

Max Activating Token Index: 849

Text #14

Max Range: 6.9364. Min Range: -6.9364

Max Act: 3.6478. Min Act: -0.0000

Data Index: 614930 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 6.9364. Min Range: -6.9364

Max Act: 3.8406. Min Act: -0.0000

Data Index: 896821 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 6.9364. Min Range: -6.9364

Max Act: 3.7825. Min Act: -0.0000

Data Index: 1264693 (C4 (Web Text))

Max Activating Token Index: 212

Text #17

Max Range: 6.9364. Min Range: -6.9364

Max Act: 3.6278. Min Act: -0.0000

Data Index: 1588841 (Python Code)

Max Activating Token Index: 834

Text #18

Max Range: 6.9364. Min Range: -6.9364

Max Act: 3.8202. Min Act: -0.0000

Data Index: 1399206 (Python Code)

Max Activating Token Index: 972

Text #19

Max Range: 6.9364. Min Range: -6.9364

Max Act: 4.0338. Min Act: -0.0000

Data Index: 130056 (C4 (Web Text))

Max Activating Token Index: 141