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

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

Neuron 1524 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: 2.5270. Min Range: -2.5270

Max Act: 2.5270. Min Act: -0.0000

Data Index: 815610 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 2.5270. Min Range: -2.5270

Max Act: 2.0345. Min Act: -0.0000

Data Index: 859713 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 2.5270. Min Range: -2.5270

Max Act: 1.8900. Min Act: -0.0000

Data Index: 1108886 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 2.5270. Min Range: -2.5270

Max Act: 1.8929. Min Act: -0.0000

Data Index: 1225780 (C4 (Web Text))

Max Activating Token Index: 739

Text #4

Max Range: 2.5270. Min Range: -2.5270

Max Act: 1.7939. Min Act: -0.0000

Data Index: 1024932 (C4 (Web Text))

Max Activating Token Index: 869

Text #5

Max Range: 2.5270. Min Range: -2.5270

Max Act: 1.8016. Min Act: -0.0000

Data Index: 1354097 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 2.5270. Min Range: -2.5270

Max Act: 1.8311. Min Act: -0.0000

Data Index: 15521 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 2.5270. Min Range: -2.5270

Max Act: 1.8375. Min Act: -0.0000

Data Index: 742362 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 2.5270. Min Range: -2.5270

Max Act: 1.6914. Min Act: -0.0000

Data Index: 1278988 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 2.5270. Min Range: -2.5270

Max Act: 1.6977. Min Act: -0.0000

Data Index: 813678 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 2.5270. Min Range: -2.5270

Max Act: 1.6251. Min Act: 0.0000

Data Index: 420236 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 2.5270. Min Range: -2.5270

Max Act: 1.6257. Min Act: -0.0000

Data Index: 1299639 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 2.5270. Min Range: -2.5270

Max Act: 1.6611. Min Act: -0.0000

Data Index: 236804 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 2.5270. Min Range: -2.5270

Max Act: 1.7851. Min Act: -0.0000

Data Index: 535215 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 2.5270. Min Range: -2.5270

Max Act: 1.7646. Min Act: -0.0000

Data Index: 162216 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 2.5270. Min Range: -2.5270

Max Act: 1.6687. Min Act: -0.0000

Data Index: 333427 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 2.5270. Min Range: -2.5270

Max Act: 1.7478. Min Act: -0.0000

Data Index: 665556 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 2.5270. Min Range: -2.5270

Max Act: 1.7985. Min Act: -0.0000

Data Index: 930050 (C4 (Web Text))

Max Activating Token Index: 1021

Text #18

Max Range: 2.5270. Min Range: -2.5270

Max Act: 1.7084. Min Act: -0.0000

Data Index: 561332 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 2.5270. Min Range: -2.5270

Max Act: 1.5267. Min Act: -0.0000

Data Index: 810501 (C4 (Web Text))

Max Activating Token Index: 651