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

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

Neuron 639 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: 0.0279. Min Range: -0.0279

Max Act: 0.0279. Min Act: -0.0006

Data Index: 1082013 (C4 (Web Text))

Max Activating Token Index: 482

Text #1

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0231. Min Act: -0.0006

Data Index: 376709 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0226. Min Act: -0.0006

Data Index: 747424 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0226. Min Act: -0.0006

Data Index: 430643 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0213. Min Act: -0.0006

Data Index: 954567 (C4 (Web Text))

Max Activating Token Index: 432

Text #5

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0208. Min Act: -0.0006

Data Index: 869543 (C4 (Web Text))

Max Activating Token Index: 356

Text #6

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0209. Min Act: -0.0006

Data Index: 776471 (C4 (Web Text))

Max Activating Token Index: 873

Text #7

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0206. Min Act: -0.0006

Data Index: 1111485 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0202. Min Act: -0.0006

Data Index: 412904 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0205. Min Act: -0.0006

Data Index: 126647 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0214. Min Act: -0.0006

Data Index: 1125238 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0204. Min Act: -0.0006

Data Index: 1006442 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0203. Min Act: -0.0006

Data Index: 644000 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0203. Min Act: -0.0006

Data Index: 874307 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0197. Min Act: -0.0006

Data Index: 1005554 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0203. Min Act: -0.0006

Data Index: 707134 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0198. Min Act: -0.0006

Data Index: 218384 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0203. Min Act: -0.0006

Data Index: 918108 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0193. Min Act: -0.0006

Data Index: 8542 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0205. Min Act: -0.0006

Data Index: 52387 (C4 (Web Text))

Max Activating Token Index: 853