Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 249 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0258. Min Act: -0.0004

Data Index: 239456 (C4 (Web Text))

Max Activating Token Index: 977

Text #1

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0202. Min Act: -0.0004

Data Index: 711819 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0203. Min Act: -0.0004

Data Index: 743390 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0211. Min Act: -0.0004

Data Index: 1250403 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0218. Min Act: -0.0004

Data Index: 1199720 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0200. Min Act: -0.0004

Data Index: 566994 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0173. Min Act: -0.0004

Data Index: 618598 (C4 (Web Text))

Max Activating Token Index: 1015

Text #7

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0188. Min Act: -0.0004

Data Index: 1447566 (Python Code)

Max Activating Token Index: 426

Text #8

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0198. Min Act: -0.0004

Data Index: 1202188 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0187. Min Act: -0.0004

Data Index: 592799 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0190. Min Act: -0.0004

Data Index: 1511440 (Python Code)

Max Activating Token Index: 673

Text #11

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0188. Min Act: -0.0004

Data Index: 1654303 (Python Code)

Max Activating Token Index: 901

Text #12

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0199. Min Act: -0.0004

Data Index: 740015 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0188. Min Act: -0.0004

Data Index: 528538 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0198. Min Act: -0.0004

Data Index: 31015 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0194. Min Act: -0.0004

Data Index: 832934 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0179. Min Act: -0.0004

Data Index: 1042792 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0188. Min Act: -0.0004

Data Index: 133067 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0181. Min Act: -0.0004

Data Index: 416983 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0185. Min Act: -0.0004

Data Index: 282794 (C4 (Web Text))

Max Activating Token Index: 236