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

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

Neuron 1948 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6247. Min Range: -1.6247

Max Act: 1.6247. Min Act: -0.0001

Data Index: 1115799 (C4 (Web Text))

Max Activating Token Index: 359

Text #1

Max Range: 1.6247. Min Range: -1.6247

Max Act: 1.3676. Min Act: -0.0001

Data Index: 789107 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 1.6247. Min Range: -1.6247

Max Act: 1.3449. Min Act: -0.0001

Data Index: 1166169 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 1.6247. Min Range: -1.6247

Max Act: 1.3934. Min Act: -0.0001

Data Index: 1176740 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 1.6247. Min Range: -1.6247

Max Act: 1.2505. Min Act: -0.0001

Data Index: 471837 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 1.6247. Min Range: -1.6247

Max Act: 1.2412. Min Act: -0.0001

Data Index: 28590 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 1.6247. Min Range: -1.6247

Max Act: 1.2751. Min Act: -0.0001

Data Index: 350688 (C4 (Web Text))

Max Activating Token Index: 954

Text #7

Max Range: 1.6247. Min Range: -1.6247

Max Act: 1.2000. Min Act: -0.0001

Data Index: 1333882 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 1.6247. Min Range: -1.6247

Max Act: 1.1873. Min Act: -0.0001

Data Index: 1141865 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 1.6247. Min Range: -1.6247

Max Act: 1.2510. Min Act: -0.0001

Data Index: 333733 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 1.6247. Min Range: -1.6247

Max Act: 1.1111. Min Act: -0.0001

Data Index: 937169 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 1.6247. Min Range: -1.6247

Max Act: 1.2067. Min Act: -0.0001

Data Index: 1239762 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 1.6247. Min Range: -1.6247

Max Act: 1.1455. Min Act: -0.0001

Data Index: 688266 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 1.6247. Min Range: -1.6247

Max Act: 1.1300. Min Act: -0.0001

Data Index: 1335256 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 1.6247. Min Range: -1.6247

Max Act: 1.2004. Min Act: -0.0001

Data Index: 1261258 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 1.6247. Min Range: -1.6247

Max Act: 1.1898. Min Act: -0.0001

Data Index: 1229252 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 1.6247. Min Range: -1.6247

Max Act: 1.2105. Min Act: -0.0001

Data Index: 1147411 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 1.6247. Min Range: -1.6247

Max Act: 1.1126. Min Act: -0.0001

Data Index: 154893 (C4 (Web Text))

Max Activating Token Index: 337

Text #18

Max Range: 1.6247. Min Range: -1.6247

Max Act: 1.1629. Min Act: -0.0001

Data Index: 574464 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 1.6247. Min Range: -1.6247

Max Act: 0.9150. Min Act: -0.0001

Data Index: 235601 (C4 (Web Text))

Max Activating Token Index: 644