Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1071 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0393. Min Act: -0.0005

Data Index: 353292 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0347. Min Act: -0.0006

Data Index: 465481 (C4 (Web Text))

Max Activating Token Index: 447

Text #2

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0282. Min Act: -0.0006

Data Index: 250049 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0284. Min Act: -0.0005

Data Index: 159601 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0283. Min Act: -0.0006

Data Index: 731617 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0285. Min Act: -0.0006

Data Index: 767061 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0296. Min Act: -0.0006

Data Index: 1247268 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0284. Min Act: -0.0006

Data Index: 826393 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0270. Min Act: -0.0006

Data Index: 162440 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0266. Min Act: -0.0006

Data Index: 128861 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0270. Min Act: -0.0006

Data Index: 266718 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0259. Min Act: -0.0006

Data Index: 315688 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0254. Min Act: -0.0006

Data Index: 64752 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0257. Min Act: -0.0006

Data Index: 912650 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0253. Min Act: -0.0006

Data Index: 379212 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0257. Min Act: -0.0006

Data Index: 177782 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0247. Min Act: -0.0006

Data Index: 715516 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0241. Min Act: -0.0006

Data Index: 597201 (C4 (Web Text))

Max Activating Token Index: 667

Text #18

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0255. Min Act: -0.0005

Data Index: 4135 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0249. Min Act: -0.0006

Data Index: 978129 (C4 (Web Text))

Max Activating Token Index: 1006