Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 531 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0556. Min Act: -0.0003

Data Index: 469457 (C4 (Web Text))

Max Activating Token Index: 725

Text #1

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0530. Min Act: -0.0003

Data Index: 83141 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0526. Min Act: -0.0004

Data Index: 23170 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0523. Min Act: -0.0003

Data Index: 66793 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0506. Min Act: -0.0003

Data Index: 154347 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0453. Min Act: -0.0003

Data Index: 458563 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0464. Min Act: -0.0003

Data Index: 115584 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0453. Min Act: -0.0003

Data Index: 1153899 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0444. Min Act: -0.0003

Data Index: 732884 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0462. Min Act: -0.0003

Data Index: 1136961 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0428. Min Act: -0.0002

Data Index: 481695 (C4 (Web Text))

Max Activating Token Index: 623

Text #11

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0430. Min Act: -0.0003

Data Index: 398235 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0423. Min Act: -0.0003

Data Index: 452002 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0476. Min Act: -0.0002

Data Index: 163252 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0427. Min Act: -0.0003

Data Index: 425648 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0421. Min Act: -0.0003

Data Index: 1289607 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1241851 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0429. Min Act: -0.0003

Data Index: 1089595 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0410. Min Act: -0.0002

Data Index: 454980 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0411. Min Act: -0.0003

Data Index: 860867 (C4 (Web Text))

Max Activating Token Index: 905