Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3519 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.9807. Min Act: -0.0001

Data Index: 95128 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7998. Min Act: -0.0001

Data Index: 491090 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7755. Min Act: -0.0001

Data Index: 645806 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.8962. Min Act: -0.0001

Data Index: 68638 (C4 (Web Text))

Max Activating Token Index: 623

Text #4

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.8190. Min Act: -0.0001

Data Index: 940432 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7710. Min Act: -0.0000

Data Index: 521269 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7383. Min Act: -0.0001

Data Index: 477167 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.8138. Min Act: -0.0000

Data Index: 713943 (C4 (Web Text))

Max Activating Token Index: 868

Text #8

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7828. Min Act: -0.0001

Data Index: 842946 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.8000. Min Act: -0.0001

Data Index: 349131 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7672. Min Act: -0.0001

Data Index: 1284910 (C4 (Web Text))

Max Activating Token Index: 492

Text #11

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7376. Min Act: -0.0001

Data Index: 508988 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7448. Min Act: -0.0001

Data Index: 871453 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7502. Min Act: -0.0001

Data Index: 797437 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.6983. Min Act: -0.0001

Data Index: 501245 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.6885. Min Act: -0.0001

Data Index: 269120 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7780. Min Act: -0.0000

Data Index: 729074 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7481. Min Act: -0.0001

Data Index: 670485 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.6923. Min Act: -0.0001

Data Index: 736236 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7548. Min Act: -0.0001

Data Index: 828041 (C4 (Web Text))

Max Activating Token Index: 656