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

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

Neuron 1971 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.8171. Min Act: -0.0000

Data Index: 747862 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.7108. Min Act: -0.0000

Data Index: 519443 (C4 (Web Text))

Max Activating Token Index: 868

Text #2

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.6807. Min Act: -0.0000

Data Index: 255390 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.7233. Min Act: -0.0000

Data Index: 305458 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.7180. Min Act: -0.0000

Data Index: 859716 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.6812. Min Act: -0.0000

Data Index: 393771 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.6595. Min Act: -0.0000

Data Index: 136847 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.6478. Min Act: -0.0000

Data Index: 887042 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.7058. Min Act: -0.0000

Data Index: 1225855 (C4 (Web Text))

Max Activating Token Index: 784

Text #9

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.6250. Min Act: -0.0000

Data Index: 58827 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.5834. Min Act: -0.0000

Data Index: 175999 (C4 (Web Text))

Max Activating Token Index: 351

Text #11

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.6379. Min Act: -0.0000

Data Index: 337249 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.6001. Min Act: -0.0000

Data Index: 986339 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.6086. Min Act: -0.0000

Data Index: 410435 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.5790. Min Act: -0.0000

Data Index: 378178 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.6371. Min Act: -0.0000

Data Index: 1001024 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.5995. Min Act: -0.0000

Data Index: 396926 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.5850. Min Act: -0.0000

Data Index: 675169 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.5767. Min Act: -0.0000

Data Index: 1353104 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.8171. Min Range: -0.8171

Max Act: 0.5670. Min Act: -0.0000

Data Index: 814573 (C4 (Web Text))

Max Activating Token Index: 267