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

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

Neuron 5440 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.9111. Min Act: -0.0002

Data Index: 94825 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.8641. Min Act: -0.0002

Data Index: 379681 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.8443. Min Act: -0.0002

Data Index: 917314 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.8310. Min Act: -0.0002

Data Index: 1173183 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.8199. Min Act: -0.0002

Data Index: 677769 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.8132. Min Act: -0.0003

Data Index: 600031 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.7844. Min Act: -0.0002

Data Index: 69896 (C4 (Web Text))

Max Activating Token Index: 636

Text #7

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.7800. Min Act: -0.0002

Data Index: 1054984 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.7419. Min Act: -0.0002

Data Index: 421975 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.7262. Min Act: -0.0002

Data Index: 603140 (C4 (Web Text))

Max Activating Token Index: 104

Text #10

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.7202. Min Act: -0.0002

Data Index: 1085611 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.7194. Min Act: -0.0002

Data Index: 1213403 (C4 (Web Text))

Max Activating Token Index: 662

Text #12

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.6977. Min Act: -0.0002

Data Index: 98987 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.7003. Min Act: -0.0002

Data Index: 1355339 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.7158. Min Act: -0.0002

Data Index: 1069998 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.7073. Min Act: -0.0002

Data Index: 1059746 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.6913. Min Act: -0.0002

Data Index: 1058836 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.6844. Min Act: -0.0002

Data Index: 957973 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.6979. Min Act: -0.0002

Data Index: 623826 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.6853. Min Act: -0.0002

Data Index: 300263 (C4 (Web Text))

Max Activating Token Index: 57