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

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

Neuron 4445 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.3550. Min Act: -0.0000

Data Index: 1034322 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.3419. Min Act: -0.0000

Data Index: 652365 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.3075. Min Act: -0.0000

Data Index: 770147 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.3045. Min Act: -0.0000

Data Index: 474038 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2647. Min Act: -0.0000

Data Index: 966721 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2526. Min Act: -0.0000

Data Index: 978175 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2655. Min Act: -0.0000

Data Index: 886052 (C4 (Web Text))

Max Activating Token Index: 131

Text #7

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2742. Min Act: -0.0000

Data Index: 467556 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2611. Min Act: -0.0000

Data Index: 938878 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2543. Min Act: -0.0000

Data Index: 5382 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2522. Min Act: -0.0000

Data Index: 753385 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2318. Min Act: -0.0000

Data Index: 1067798 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2498. Min Act: -0.0000

Data Index: 468934 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2560. Min Act: -0.0000

Data Index: 1114404 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2471. Min Act: -0.0000

Data Index: 871916 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2423. Min Act: -0.0000

Data Index: 671007 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2258. Min Act: -0.0000

Data Index: 584635 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2406. Min Act: -0.0000

Data Index: 1306388 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2383. Min Act: -0.0000

Data Index: 826661 (C4 (Web Text))

Max Activating Token Index: 417

Text #19

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2459. Min Act: -0.0000

Data Index: 97862 (C4 (Web Text))

Max Activating Token Index: 903