Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2621 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0501. Min Act: -0.0003

Data Index: 787721 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0516. Min Act: -0.0003

Data Index: 699466 (C4 (Web Text))

Max Activating Token Index: 902

Text #2

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0389. Min Act: -0.0003

Data Index: 459032 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0471. Min Act: -0.0003

Data Index: 831334 (C4 (Web Text))

Max Activating Token Index: 529

Text #4

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0484. Min Act: -0.0003

Data Index: 626394 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0462. Min Act: -0.0003

Data Index: 352140 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0453. Min Act: -0.0003

Data Index: 895153 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0393. Min Act: -0.0003

Data Index: 352970 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0374. Min Act: -0.0003

Data Index: 923441 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0470. Min Act: -0.0003

Data Index: 274743 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0423. Min Act: -0.0003

Data Index: 1002375 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0387. Min Act: -0.0003

Data Index: 121705 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0426. Min Act: -0.0003

Data Index: 499082 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0391. Min Act: -0.0003

Data Index: 421175 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0386. Min Act: -0.0003

Data Index: 270759 (C4 (Web Text))

Max Activating Token Index: 658

Text #15

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0418. Min Act: -0.0003

Data Index: 150554 (C4 (Web Text))

Max Activating Token Index: 422

Text #16

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0430. Min Act: -0.0003

Data Index: 473624 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0399. Min Act: -0.0003

Data Index: 581619 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0383. Min Act: -0.0003

Data Index: 164223 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0408. Min Act: -0.0003

Data Index: 713733 (C4 (Web Text))

Max Activating Token Index: 272