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

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

Neuron 3803 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1710. Min Act: -0.0000

Data Index: 255886 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1536. Min Act: -0.0000

Data Index: 51714 (C4 (Web Text))

Max Activating Token Index: 482

Text #2

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1466. Min Act: -0.0000

Data Index: 228506 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1474. Min Act: -0.0000

Data Index: 1180910 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1426. Min Act: 0.0000

Data Index: 943973 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1388. Min Act: -0.0000

Data Index: 1049104 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1184. Min Act: -0.0000

Data Index: 315906 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1373. Min Act: -0.0000

Data Index: 1258892 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1290. Min Act: -0.0000

Data Index: 1067818 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1264. Min Act: -0.0000

Data Index: 884441 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1217. Min Act: -0.0000

Data Index: 1064601 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1236. Min Act: -0.0000

Data Index: 685964 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1160. Min Act: -0.0000

Data Index: 573791 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1275. Min Act: -0.0000

Data Index: 418631 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1144. Min Act: -0.0000

Data Index: 1087661 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1196. Min Act: -0.0000

Data Index: 1021215 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1207. Min Act: -0.0000

Data Index: 637484 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1200. Min Act: -0.0000

Data Index: 241019 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1197. Min Act: -0.0000

Data Index: 114735 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 0.1710. Min Range: -0.1710

Max Act: 0.1077. Min Act: -0.0000

Data Index: 292391 (C4 (Web Text))

Max Activating Token Index: 234