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

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

Neuron 813 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.9438. Min Act: -0.0000

Data Index: 508765 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.9562. Min Act: -0.0000

Data Index: 356697 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.8297. Min Act: -0.0000

Data Index: 760571 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.7702. Min Act: -0.0000

Data Index: 864125 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.6975. Min Act: -0.0000

Data Index: 14760 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.7315. Min Act: -0.0000

Data Index: 663220 (C4 (Web Text))

Max Activating Token Index: 291

Text #6

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.6988. Min Act: -0.0000

Data Index: 66921 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.6498. Min Act: -0.0000

Data Index: 175905 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.6277. Min Act: -0.0000

Data Index: 1043985 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.6089. Min Act: -0.0000

Data Index: 244129 (C4 (Web Text))

Max Activating Token Index: 436

Text #10

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.5857. Min Act: -0.0000

Data Index: 507116 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.5650. Min Act: -0.0000

Data Index: 157366 (C4 (Web Text))

Max Activating Token Index: 426

Text #12

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.5705. Min Act: 0.0000

Data Index: 1051631 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.5607. Min Act: -0.0000

Data Index: 1074884 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.5621. Min Act: -0.0000

Data Index: 467610 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.5511. Min Act: -0.0000

Data Index: 1158078 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.5450. Min Act: -0.0000

Data Index: 1085709 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.5409. Min Act: -0.0000

Data Index: 1059079 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.4831. Min Act: -0.0000

Data Index: 1098549 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.5757. Min Act: -0.0000

Data Index: 108161 (C4 (Web Text))

Max Activating Token Index: 281