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

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

Neuron 594 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3526. Min Range: -1.3526

Max Act: 1.3370. Min Act: -0.0002

Data Index: 808068 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 1.3526. Min Range: -1.3526

Max Act: 1.3526. Min Act: -0.0002

Data Index: 400204 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 1.3526. Min Range: -1.3526

Max Act: 1.1149. Min Act: -0.0002

Data Index: 1011149 (C4 (Web Text))

Max Activating Token Index: 856

Text #3

Max Range: 1.3526. Min Range: -1.3526

Max Act: 1.0380. Min Act: -0.0002

Data Index: 281525 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 1.3526. Min Range: -1.3526

Max Act: 1.1822. Min Act: -0.0002

Data Index: 768295 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 1.3526. Min Range: -1.3526

Max Act: 1.0734. Min Act: -0.0002

Data Index: 663927 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 1.3526. Min Range: -1.3526

Max Act: 0.8264. Min Act: -0.0002

Data Index: 596837 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 1.3526. Min Range: -1.3526

Max Act: 0.8626. Min Act: -0.0002

Data Index: 467046 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 1.3526. Min Range: -1.3526

Max Act: 1.0172. Min Act: -0.0002

Data Index: 53242 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 1.3526. Min Range: -1.3526

Max Act: 1.0031. Min Act: -0.0002

Data Index: 976743 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 1.3526. Min Range: -1.3526

Max Act: 1.2224. Min Act: -0.0002

Data Index: 1205060 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 1.3526. Min Range: -1.3526

Max Act: 0.9549. Min Act: -0.0002

Data Index: 955116 (C4 (Web Text))

Max Activating Token Index: 320

Text #12

Max Range: 1.3526. Min Range: -1.3526

Max Act: 1.0100. Min Act: -0.0002

Data Index: 340945 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 1.3526. Min Range: -1.3526

Max Act: 0.9755. Min Act: -0.0002

Data Index: 88548 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 1.3526. Min Range: -1.3526

Max Act: 1.0233. Min Act: -0.0002

Data Index: 1113645 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 1.3526. Min Range: -1.3526

Max Act: 1.0100. Min Act: -0.0002

Data Index: 900359 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 1.3526. Min Range: -1.3526

Max Act: 1.0217. Min Act: -0.0002

Data Index: 726683 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 1.3526. Min Range: -1.3526

Max Act: 0.9667. Min Act: -0.0002

Data Index: 372815 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 1.3526. Min Range: -1.3526

Max Act: 0.9753. Min Act: -0.0002

Data Index: 780322 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 1.3526. Min Range: -1.3526

Max Act: 0.7737. Min Act: -0.0002

Data Index: 125854 (C4 (Web Text))

Max Activating Token Index: 810