Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 904 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.9752. Min Act: -0.0000

Data Index: 518626 (C4 (Web Text))

Max Activating Token Index: 543

Text #1

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.6720. Min Act: -0.0000

Data Index: 523479 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.6189. Min Act: -0.0000

Data Index: 401486 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.6243. Min Act: -0.0000

Data Index: 375986 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.6284. Min Act: -0.0000

Data Index: 1115433 (C4 (Web Text))

Max Activating Token Index: 823

Text #5

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.5977. Min Act: -0.0000

Data Index: 305851 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.5182. Min Act: -0.0000

Data Index: 1298209 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.5510. Min Act: -0.0000

Data Index: 1142386 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.5573. Min Act: -0.0000

Data Index: 1203749 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.5380. Min Act: -0.0000

Data Index: 926231 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.5888. Min Act: -0.0000

Data Index: 342559 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.5280. Min Act: -0.0000

Data Index: 181747 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.5043. Min Act: -0.0000

Data Index: 74297 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.5182. Min Act: -0.0000

Data Index: 307007 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.5358. Min Act: -0.0000

Data Index: 1082464 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.4906. Min Act: -0.0000

Data Index: 967630 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.5000. Min Act: -0.0000

Data Index: 840995 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.5380. Min Act: -0.0000

Data Index: 75125 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.5161. Min Act: -0.0000

Data Index: 365787 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.5265. Min Act: -0.0000

Data Index: 930813 (C4 (Web Text))

Max Activating Token Index: 871