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

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

Neuron 3549 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9155. Min Range: -1.9155

Max Act: 1.9155. Min Act: -0.0000

Data Index: 729147 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 1.9155. Min Range: -1.9155

Max Act: 1.9068. Min Act: -0.0000

Data Index: 376035 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 1.9155. Min Range: -1.9155

Max Act: 1.7781. Min Act: -0.0000

Data Index: 270347 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 1.9155. Min Range: -1.9155

Max Act: 1.7729. Min Act: -0.0000

Data Index: 414556 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 1.9155. Min Range: -1.9155

Max Act: 1.6233. Min Act: -0.0000

Data Index: 800885 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 1.9155. Min Range: -1.9155

Max Act: 1.6733. Min Act: -0.0000

Data Index: 1180977 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 1.9155. Min Range: -1.9155

Max Act: 1.6455. Min Act: -0.0000

Data Index: 846137 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 1.9155. Min Range: -1.9155

Max Act: 1.5935. Min Act: -0.0000

Data Index: 1347047 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 1.9155. Min Range: -1.9155

Max Act: 1.3867. Min Act: -0.0000

Data Index: 964463 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 1.9155. Min Range: -1.9155

Max Act: 1.4614. Min Act: -0.0000

Data Index: 1217393 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 1.9155. Min Range: -1.9155

Max Act: 1.4228. Min Act: -0.0000

Data Index: 1358709 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 1.9155. Min Range: -1.9155

Max Act: 1.4022. Min Act: -0.0000

Data Index: 650899 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 1.9155. Min Range: -1.9155

Max Act: 1.3066. Min Act: -0.0000

Data Index: 430439 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 1.9155. Min Range: -1.9155

Max Act: 1.2896. Min Act: -0.0000

Data Index: 288977 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 1.9155. Min Range: -1.9155

Max Act: 1.2695. Min Act: 0.0000

Data Index: 824615 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 1.9155. Min Range: -1.9155

Max Act: 1.1602. Min Act: -0.0000

Data Index: 1263924 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 1.9155. Min Range: -1.9155

Max Act: 1.2329. Min Act: -0.0000

Data Index: 343541 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 1.9155. Min Range: -1.9155

Max Act: 1.2120. Min Act: -0.0000

Data Index: 11688 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 1.9155. Min Range: -1.9155

Max Act: 1.1563. Min Act: -0.0000

Data Index: 364542 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 1.9155. Min Range: -1.9155

Max Act: 1.1355. Min Act: -0.0000

Data Index: 1112279 (C4 (Web Text))

Max Activating Token Index: 202