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

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

Neuron 4995 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.8252. Min Act: -0.0000

Data Index: 1341642 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.6137. Min Act: -0.0000

Data Index: 812205 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.6150. Min Act: -0.0000

Data Index: 1139963 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.6053. Min Act: -0.0000

Data Index: 871227 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.5863. Min Act: -0.0000

Data Index: 357441 (C4 (Web Text))

Max Activating Token Index: 803

Text #5

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.6163. Min Act: -0.0000

Data Index: 280158 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.6240. Min Act: -0.0000

Data Index: 786662 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.6012. Min Act: -0.0000

Data Index: 403667 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.5740. Min Act: -0.0000

Data Index: 618184 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.5708. Min Act: -0.0000

Data Index: 649621 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.5528. Min Act: -0.0000

Data Index: 1225309 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.5522. Min Act: -0.0000

Data Index: 620381 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.5983. Min Act: -0.0000

Data Index: 759525 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.5696. Min Act: -0.0000

Data Index: 424285 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.5665. Min Act: -0.0000

Data Index: 38702 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.5234. Min Act: -0.0000

Data Index: 208862 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.5470. Min Act: -0.0000

Data Index: 439733 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.5250. Min Act: -0.0000

Data Index: 668323 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.5256. Min Act: -0.0000

Data Index: 455223 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.5454. Min Act: -0.0000

Data Index: 952987 (C4 (Web Text))

Max Activating Token Index: 779