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

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

Neuron 3484 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6506. Min Range: -2.6506

Max Act: 2.6506. Min Act: -0.0000

Data Index: 1048964 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 2.6506. Min Range: -2.6506

Max Act: 2.4573. Min Act: -0.0000

Data Index: 1035005 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 2.6506. Min Range: -2.6506

Max Act: 2.2503. Min Act: -0.0000

Data Index: 175411 (C4 (Web Text))

Max Activating Token Index: 935

Text #3

Max Range: 2.6506. Min Range: -2.6506

Max Act: 2.2984. Min Act: -0.0000

Data Index: 28023 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 2.6506. Min Range: -2.6506

Max Act: 2.2745. Min Act: -0.0000

Data Index: 591218 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 2.6506. Min Range: -2.6506

Max Act: 2.5210. Min Act: -0.0000

Data Index: 1134834 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 2.6506. Min Range: -2.6506

Max Act: 1.9759. Min Act: -0.0000

Data Index: 285090 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 2.6506. Min Range: -2.6506

Max Act: 2.1543. Min Act: -0.0000

Data Index: 212714 (C4 (Web Text))

Max Activating Token Index: 329

Text #8

Max Range: 2.6506. Min Range: -2.6506

Max Act: 2.0705. Min Act: -0.0000

Data Index: 774273 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 2.6506. Min Range: -2.6506

Max Act: 1.9441. Min Act: -0.0000

Data Index: 434040 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 2.6506. Min Range: -2.6506

Max Act: 2.0540. Min Act: -0.0000

Data Index: 186069 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 2.6506. Min Range: -2.6506

Max Act: 1.9257. Min Act: -0.0000

Data Index: 1079139 (C4 (Web Text))

Max Activating Token Index: 821

Text #12

Max Range: 2.6506. Min Range: -2.6506

Max Act: 1.9032. Min Act: -0.0000

Data Index: 492263 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 2.6506. Min Range: -2.6506

Max Act: 2.0014. Min Act: -0.0000

Data Index: 222619 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 2.6506. Min Range: -2.6506

Max Act: 2.0561. Min Act: -0.0000

Data Index: 919373 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 2.6506. Min Range: -2.6506

Max Act: 1.9503. Min Act: -0.0000

Data Index: 469152 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 2.6506. Min Range: -2.6506

Max Act: 1.9386. Min Act: -0.0000

Data Index: 356146 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 2.6506. Min Range: -2.6506

Max Act: 1.9289. Min Act: -0.0000

Data Index: 1082577 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 2.6506. Min Range: -2.6506

Max Act: 1.9337. Min Act: -0.0000

Data Index: 1218900 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 2.6506. Min Range: -2.6506

Max Act: 1.9263. Min Act: -0.0000

Data Index: 1234170 (C4 (Web Text))

Max Activating Token Index: 393