Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1024 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0409. Min Act: -0.0005

Data Index: 1265990 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0410. Min Act: -0.0005

Data Index: 700069 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0393. Min Act: -0.0005

Data Index: 1246504 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0419. Min Act: -0.0005

Data Index: 1279672 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0393. Min Act: -0.0005

Data Index: 1347498 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0382. Min Act: -0.0005

Data Index: 1059196 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0376. Min Act: -0.0005

Data Index: 251256 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0377. Min Act: -0.0005

Data Index: 644546 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0397. Min Act: -0.0005

Data Index: 543168 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0367. Min Act: -0.0005

Data Index: 275571 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0375. Min Act: -0.0004

Data Index: 630915 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0378. Min Act: -0.0005

Data Index: 941488 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0386. Min Act: -0.0005

Data Index: 1178192 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0372. Min Act: -0.0005

Data Index: 1018014 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0339. Min Act: -0.0005

Data Index: 289329 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0367. Min Act: -0.0005

Data Index: 1326957 (C4 (Web Text))

Max Activating Token Index: 792

Text #16

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0371. Min Act: -0.0005

Data Index: 1337414 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0373. Min Act: -0.0005

Data Index: 59591 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0370. Min Act: -0.0005

Data Index: 406796 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0366. Min Act: -0.0005

Data Index: 27243 (C4 (Web Text))

Max Activating Token Index: 800