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

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

Neuron 1236 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: 3.1648. Min Range: -3.1648

Max Act: 3.1648. Min Act: -0.0000

Data Index: 81048 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 3.1648. Min Range: -3.1648

Max Act: 2.6377. Min Act: -0.0000

Data Index: 968371 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 3.1648. Min Range: -3.1648

Max Act: 2.2109. Min Act: -0.0000

Data Index: 814814 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 3.1648. Min Range: -3.1648

Max Act: 2.2007. Min Act: -0.0000

Data Index: 1320967 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 3.1648. Min Range: -3.1648

Max Act: 2.1767. Min Act: -0.0000

Data Index: 1281846 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 3.1648. Min Range: -3.1648

Max Act: 2.0336. Min Act: -0.0000

Data Index: 384391 (C4 (Web Text))

Max Activating Token Index: 450

Text #6

Max Range: 3.1648. Min Range: -3.1648

Max Act: 2.1340. Min Act: -0.0000

Data Index: 1136142 (C4 (Web Text))

Max Activating Token Index: 351

Text #7

Max Range: 3.1648. Min Range: -3.1648

Max Act: 1.9887. Min Act: -0.0000

Data Index: 360308 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 3.1648. Min Range: -3.1648

Max Act: 2.2438. Min Act: -0.0000

Data Index: 639064 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 3.1648. Min Range: -3.1648

Max Act: 1.9792. Min Act: -0.0000

Data Index: 135033 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 3.1648. Min Range: -3.1648

Max Act: 2.0929. Min Act: -0.0000

Data Index: 980437 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 3.1648. Min Range: -3.1648

Max Act: 2.0791. Min Act: -0.0000

Data Index: 457425 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 3.1648. Min Range: -3.1648

Max Act: 2.1193. Min Act: -0.0000

Data Index: 182322 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 3.1648. Min Range: -3.1648

Max Act: 1.9287. Min Act: -0.0000

Data Index: 1049815 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 3.1648. Min Range: -3.1648

Max Act: 2.0514. Min Act: -0.0000

Data Index: 1059279 (C4 (Web Text))

Max Activating Token Index: 415

Text #15

Max Range: 3.1648. Min Range: -3.1648

Max Act: 2.0934. Min Act: -0.0000

Data Index: 769933 (C4 (Web Text))

Max Activating Token Index: 97

Text #16

Max Range: 3.1648. Min Range: -3.1648

Max Act: 1.8170. Min Act: -0.0000

Data Index: 72260 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 3.1648. Min Range: -3.1648

Max Act: 2.1465. Min Act: -0.0000

Data Index: 858501 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 3.1648. Min Range: -3.1648

Max Act: 1.9455. Min Act: -0.0000

Data Index: 1200930 (C4 (Web Text))

Max Activating Token Index: 816

Text #19

Max Range: 3.1648. Min Range: -3.1648

Max Act: 1.9924. Min Act: -0.0000

Data Index: 10814 (C4 (Web Text))

Max Activating Token Index: 469