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

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

Neuron 1824 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0302. Min Act: -0.0006

Data Index: 712213 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0287. Min Act: -0.0006

Data Index: 1028633 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0287. Min Act: -0.0006

Data Index: 665376 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0284. Min Act: -0.0006

Data Index: 146233 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0284. Min Act: -0.0006

Data Index: 223426 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0282. Min Act: -0.0006

Data Index: 784919 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0277. Min Act: -0.0006

Data Index: 1215512 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0282. Min Act: -0.0006

Data Index: 654815 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0279. Min Act: -0.0006

Data Index: 1288791 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0272. Min Act: -0.0006

Data Index: 1235531 (C4 (Web Text))

Max Activating Token Index: 567

Text #10

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0275. Min Act: -0.0006

Data Index: 1270529 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0273. Min Act: -0.0006

Data Index: 440554 (C4 (Web Text))

Max Activating Token Index: 644

Text #12

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0277. Min Act: -0.0006

Data Index: 480106 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0271. Min Act: -0.0006

Data Index: 518944 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0264. Min Act: -0.0006

Data Index: 556573 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0268. Min Act: -0.0006

Data Index: 193364 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0268. Min Act: -0.0006

Data Index: 432986 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0266. Min Act: -0.0006

Data Index: 759548 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0267. Min Act: -0.0006

Data Index: 1012532 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0266. Min Act: -0.0006

Data Index: 170332 (C4 (Web Text))

Max Activating Token Index: 838