Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2157 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0423. Min Act: -0.0002

Data Index: 45565 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0326. Min Act: -0.0002

Data Index: 1190875 (C4 (Web Text))

Max Activating Token Index: 568

Text #2

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0292. Min Act: -0.0002

Data Index: 839582 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0281. Min Act: -0.0002

Data Index: 603037 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0274. Min Act: -0.0002

Data Index: 1290113 (C4 (Web Text))

Max Activating Token Index: 803

Text #5

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0311. Min Act: -0.0002

Data Index: 350562 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0266. Min Act: -0.0002

Data Index: 950655 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0281. Min Act: -0.0002

Data Index: 1029355 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0265. Min Act: -0.0002

Data Index: 1254695 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0274. Min Act: -0.0002

Data Index: 1199219 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0267. Min Act: -0.0002

Data Index: 1176571 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0267. Min Act: -0.0002

Data Index: 661755 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0244. Min Act: -0.0002

Data Index: 1051255 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0256. Min Act: -0.0002

Data Index: 1165504 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0270. Min Act: -0.0002

Data Index: 570756 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0237. Min Act: -0.0002

Data Index: 610135 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0255. Min Act: -0.0002

Data Index: 961798 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0270. Min Act: -0.0002

Data Index: 859911 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0247. Min Act: -0.0002

Data Index: 649466 (C4 (Web Text))

Max Activating Token Index: 327

Text #19

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0237. Min Act: -0.0002

Data Index: 956836 (C4 (Web Text))

Max Activating Token Index: 762