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

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

Neuron 3253 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.8668. Min Act: -0.0000

Data Index: 1121252 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.8351. Min Act: -0.0000

Data Index: 1270649 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.7768. Min Act: -0.0000

Data Index: 720730 (C4 (Web Text))

Max Activating Token Index: 831

Text #3

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.8308. Min Act: -0.0000

Data Index: 1221302 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.7552. Min Act: -0.0000

Data Index: 552083 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.7156. Min Act: -0.0000

Data Index: 347174 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.7652. Min Act: -0.0000

Data Index: 780021 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.7517. Min Act: -0.0000

Data Index: 179395 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.7011. Min Act: -0.0000

Data Index: 52127 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.7434. Min Act: -0.0000

Data Index: 1112610 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.7168. Min Act: -0.0000

Data Index: 358948 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6829. Min Act: -0.0000

Data Index: 1285260 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6605. Min Act: -0.0000

Data Index: 299584 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6820. Min Act: -0.0000

Data Index: 977934 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.7222. Min Act: -0.0000

Data Index: 246696 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6981. Min Act: -0.0000

Data Index: 167459 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6927. Min Act: -0.0000

Data Index: 64184 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.7125. Min Act: -0.0000

Data Index: 1309540 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.7133. Min Act: -0.0000

Data Index: 164055 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6898. Min Act: -0.0000

Data Index: 427903 (C4 (Web Text))

Max Activating Token Index: 182