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

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

Neuron 2166 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.6937. Min Act: -0.0001

Data Index: 509861 (C4 (Web Text))

Max Activating Token Index: 914

Text #1

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.7000. Min Act: -0.0001

Data Index: 887472 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.7283. Min Act: -0.0001

Data Index: 649166 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.5192. Min Act: -0.0001

Data Index: 866406 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.3477. Min Act: -0.0001

Data Index: 1237851 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.3266. Min Act: -0.0001

Data Index: 159207 (C4 (Web Text))

Max Activating Token Index: 359

Text #6

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.4315. Min Act: -0.0001

Data Index: 1331816 (C4 (Web Text))

Max Activating Token Index: 544

Text #7

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.3780. Min Act: -0.0001

Data Index: 155144 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.4300. Min Act: -0.0001

Data Index: 1038626 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.2745. Min Act: -0.0001

Data Index: 141762 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.3316. Min Act: -0.0001

Data Index: 1041340 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.4447. Min Act: -0.0001

Data Index: 142378 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.3044. Min Act: -0.0001

Data Index: 1295242 (C4 (Web Text))

Max Activating Token Index: 356

Text #13

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.3558. Min Act: -0.0001

Data Index: 141797 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.2259. Min Act: -0.0001

Data Index: 895410 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.1852. Min Act: -0.0001

Data Index: 861070 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.2987. Min Act: -0.0001

Data Index: 1173793 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.2888. Min Act: -0.0001

Data Index: 1046194 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.3381. Min Act: -0.0001

Data Index: 347561 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 1.7283. Min Range: -1.7283

Max Act: 1.3693. Min Act: -0.0001

Data Index: 953128 (C4 (Web Text))

Max Activating Token Index: 64