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

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

Neuron 3811 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: 2.8694. Min Range: -2.8694

Max Act: 2.8694. Min Act: -0.0000

Data Index: 299535 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 2.8694. Min Range: -2.8694

Max Act: 2.6572. Min Act: -0.0000

Data Index: 1316344 (C4 (Web Text))

Max Activating Token Index: 473

Text #2

Max Range: 2.8694. Min Range: -2.8694

Max Act: 2.5397. Min Act: -0.0000

Data Index: 1080820 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 2.8694. Min Range: -2.8694

Max Act: 2.4611. Min Act: -0.0000

Data Index: 295499 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 2.8694. Min Range: -2.8694

Max Act: 2.2994. Min Act: -0.0000

Data Index: 904959 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 2.8694. Min Range: -2.8694

Max Act: 2.3184. Min Act: -0.0000

Data Index: 1160305 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 2.8694. Min Range: -2.8694

Max Act: 2.2923. Min Act: -0.0000

Data Index: 980041 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 2.8694. Min Range: -2.8694

Max Act: 2.2643. Min Act: -0.0000

Data Index: 992346 (C4 (Web Text))

Max Activating Token Index: 547

Text #8

Max Range: 2.8694. Min Range: -2.8694

Max Act: 2.2058. Min Act: -0.0000

Data Index: 1264670 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 2.8694. Min Range: -2.8694

Max Act: 2.3360. Min Act: -0.0000

Data Index: 1241307 (C4 (Web Text))

Max Activating Token Index: 559

Text #10

Max Range: 2.8694. Min Range: -2.8694

Max Act: 2.1929. Min Act: -0.0000

Data Index: 839025 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 2.8694. Min Range: -2.8694

Max Act: 2.1811. Min Act: -0.0000

Data Index: 900801 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 2.8694. Min Range: -2.8694

Max Act: 2.1640. Min Act: -0.0000

Data Index: 234698 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 2.8694. Min Range: -2.8694

Max Act: 2.0325. Min Act: -0.0000

Data Index: 56678 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 2.8694. Min Range: -2.8694

Max Act: 2.0754. Min Act: -0.0000

Data Index: 1439 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 2.8694. Min Range: -2.8694

Max Act: 1.9570. Min Act: -0.0000

Data Index: 405212 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 2.8694. Min Range: -2.8694

Max Act: 2.0666. Min Act: -0.0000

Data Index: 1098870 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 2.8694. Min Range: -2.8694

Max Act: 2.1527. Min Act: -0.0000

Data Index: 906369 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 2.8694. Min Range: -2.8694

Max Act: 1.9148. Min Act: -0.0000

Data Index: 1226972 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 2.8694. Min Range: -2.8694

Max Act: 1.9832. Min Act: -0.0000

Data Index: 915496 (C4 (Web Text))

Max Activating Token Index: 947