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

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

Neuron 2294 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7679. Min Range: -5.7679

Max Act: 5.7679. Min Act: -0.0000

Data Index: 273190 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 5.7679. Min Range: -5.7679

Max Act: 5.0208. Min Act: -0.0000

Data Index: 571013 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 5.7679. Min Range: -5.7679

Max Act: 5.2853. Min Act: -0.0000

Data Index: 47460 (C4 (Web Text))

Max Activating Token Index: 676

Text #3

Max Range: 5.7679. Min Range: -5.7679

Max Act: 5.0844. Min Act: -0.0001

Data Index: 480253 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 5.7679. Min Range: -5.7679

Max Act: 4.8630. Min Act: -0.0001

Data Index: 410945 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 5.7679. Min Range: -5.7679

Max Act: 4.4163. Min Act: -0.0000

Data Index: 658919 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 5.7679. Min Range: -5.7679

Max Act: 4.4792. Min Act: -0.0000

Data Index: 1316866 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 5.7679. Min Range: -5.7679

Max Act: 4.2992. Min Act: -0.0000

Data Index: 1133828 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 5.7679. Min Range: -5.7679

Max Act: 4.2891. Min Act: -0.0001

Data Index: 899232 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 5.7679. Min Range: -5.7679

Max Act: 4.2726. Min Act: -0.0001

Data Index: 1149174 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 5.7679. Min Range: -5.7679

Max Act: 3.8971. Min Act: -0.0000

Data Index: 238003 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 5.7679. Min Range: -5.7679

Max Act: 4.1680. Min Act: -0.0001

Data Index: 284157 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 5.7679. Min Range: -5.7679

Max Act: 3.9819. Min Act: -0.0001

Data Index: 241397 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 5.7679. Min Range: -5.7679

Max Act: 3.9440. Min Act: -0.0001

Data Index: 83358 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 5.7679. Min Range: -5.7679

Max Act: 3.8324. Min Act: -0.0001

Data Index: 1208418 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 5.7679. Min Range: -5.7679

Max Act: 3.7225. Min Act: -0.0000

Data Index: 508594 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 5.7679. Min Range: -5.7679

Max Act: 3.7406. Min Act: -0.0000

Data Index: 148022 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 5.7679. Min Range: -5.7679

Max Act: 3.8501. Min Act: -0.0001

Data Index: 458926 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 5.7679. Min Range: -5.7679

Max Act: 3.6870. Min Act: -0.0001

Data Index: 347265 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 5.7679. Min Range: -5.7679

Max Act: 3.6726. Min Act: -0.0001

Data Index: 1246674 (C4 (Web Text))

Max Activating Token Index: 199