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

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

Neuron 1708 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.4234. Min Act: -0.0001

Data Index: 867292 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.4296. Min Act: -0.0001

Data Index: 200260 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.4296. Min Act: -0.0001

Data Index: 119872 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.4131. Min Act: -0.0001

Data Index: 843709 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.4187. Min Act: -0.0001

Data Index: 706300 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.4194. Min Act: -0.0001

Data Index: 144075 (C4 (Web Text))

Max Activating Token Index: 889

Text #6

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.3914. Min Act: -0.0001

Data Index: 309592 (C4 (Web Text))

Max Activating Token Index: 873

Text #7

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.3989. Min Act: -0.0001

Data Index: 287681 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.4127. Min Act: -0.0001

Data Index: 455063 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.4045. Min Act: -0.0001

Data Index: 612037 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.4066. Min Act: -0.0001

Data Index: 1050532 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.4008. Min Act: -0.0001

Data Index: 770578 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.4010. Min Act: -0.0001

Data Index: 538881 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.3873. Min Act: -0.0001

Data Index: 332055 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.3850. Min Act: -0.0001

Data Index: 173387 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.3960. Min Act: -0.0001

Data Index: 716582 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.3827. Min Act: -0.0001

Data Index: 15415 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.3975. Min Act: -0.0001

Data Index: 616769 (C4 (Web Text))

Max Activating Token Index: 8

Text #18

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.3948. Min Act: -0.0001

Data Index: 889216 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.3925. Min Act: -0.0001

Data Index: 1177330 (C4 (Web Text))

Max Activating Token Index: 868