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

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

Neuron 5571 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8794. Min Range: -1.8794

Max Act: 1.7714. Min Act: -0.0002

Data Index: 1391285 (Python Code)

Max Activating Token Index: 364

Text #1

Max Range: 1.8794. Min Range: -1.8794

Max Act: 1.5410. Min Act: -0.0002

Data Index: 225143 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 1.8794. Min Range: -1.8794

Max Act: 1.7887. Min Act: -0.0002

Data Index: 1486977 (Python Code)

Max Activating Token Index: 507

Text #3

Max Range: 1.8794. Min Range: -1.8794

Max Act: 1.8794. Min Act: -0.0002

Data Index: 1611749 (Python Code)

Max Activating Token Index: 382

Text #4

Max Range: 1.8794. Min Range: -1.8794

Max Act: 1.8178. Min Act: -0.0002

Data Index: 1632677 (Python Code)

Max Activating Token Index: 259

Text #5

Max Range: 1.8794. Min Range: -1.8794

Max Act: 1.7226. Min Act: -0.0002

Data Index: 1557774 (Python Code)

Max Activating Token Index: 262

Text #6

Max Range: 1.8794. Min Range: -1.8794

Max Act: 1.7847. Min Act: -0.0002

Data Index: 1451478 (Python Code)

Max Activating Token Index: 608

Text #7

Max Range: 1.8794. Min Range: -1.8794

Max Act: 1.7886. Min Act: -0.0002

Data Index: 1533599 (Python Code)

Max Activating Token Index: 570

Text #8

Max Range: 1.8794. Min Range: -1.8794

Max Act: 1.7299. Min Act: -0.0002

Data Index: 1560007 (Python Code)

Max Activating Token Index: 341

Text #9

Max Range: 1.8794. Min Range: -1.8794

Max Act: 1.6362. Min Act: -0.0002

Data Index: 1385086 (Python Code)

Max Activating Token Index: 699

Text #10

Max Range: 1.8794. Min Range: -1.8794

Max Act: 1.5888. Min Act: -0.0002

Data Index: 1568863 (Python Code)

Max Activating Token Index: 249

Text #11

Max Range: 1.8794. Min Range: -1.8794

Max Act: 1.7303. Min Act: -0.0002

Data Index: 1486755 (Python Code)

Max Activating Token Index: 700

Text #12

Max Range: 1.8794. Min Range: -1.8794

Max Act: 1.7150. Min Act: -0.0002

Data Index: 1374925 (Python Code)

Max Activating Token Index: 256

Text #13

Max Range: 1.8794. Min Range: -1.8794

Max Act: 1.7263. Min Act: -0.0002

Data Index: 1454893 (Python Code)

Max Activating Token Index: 890

Text #14

Max Range: 1.8794. Min Range: -1.8794

Max Act: 1.5421. Min Act: -0.0002

Data Index: 1145393 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 1.8794. Min Range: -1.8794

Max Act: 1.6700. Min Act: -0.0002

Data Index: 1647076 (Python Code)

Max Activating Token Index: 181

Text #16

Max Range: 1.8794. Min Range: -1.8794

Max Act: 1.5655. Min Act: -0.0002

Data Index: 1373903 (Python Code)

Max Activating Token Index: 193

Text #17

Max Range: 1.8794. Min Range: -1.8794

Max Act: 1.5029. Min Act: -0.0002

Data Index: 1635380 (Python Code)

Max Activating Token Index: 414

Text #18

Max Range: 1.8794. Min Range: -1.8794

Max Act: 1.6212. Min Act: -0.0002

Data Index: 1640108 (Python Code)

Max Activating Token Index: 819

Text #19

Max Range: 1.8794. Min Range: -1.8794

Max Act: 1.7202. Min Act: -0.0002

Data Index: 1616131 (Python Code)

Max Activating Token Index: 202