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

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

Neuron 2514 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0628. Min Act: -0.0002

Data Index: 415673 (C4 (Web Text))

Max Activating Token Index: 641

Text #1

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0551. Min Act: -0.0002

Data Index: 48517 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0570. Min Act: -0.0002

Data Index: 882013 (C4 (Web Text))

Max Activating Token Index: 497

Text #3

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0538. Min Act: -0.0002

Data Index: 966746 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0555. Min Act: -0.0002

Data Index: 462939 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0550. Min Act: -0.0002

Data Index: 1299935 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0523. Min Act: -0.0002

Data Index: 1090805 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0522. Min Act: -0.0002

Data Index: 1289146 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0526. Min Act: -0.0002

Data Index: 713341 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0531. Min Act: -0.0002

Data Index: 278799 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0533. Min Act: -0.0002

Data Index: 925763 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0495. Min Act: -0.0002

Data Index: 606663 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0530. Min Act: -0.0002

Data Index: 400623 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0507. Min Act: -0.0002

Data Index: 58131 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0542. Min Act: -0.0002

Data Index: 913443 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0535. Min Act: -0.0002

Data Index: 286307 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0516. Min Act: -0.0002

Data Index: 985110 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0496. Min Act: -0.0002

Data Index: 228527 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0493. Min Act: -0.0002

Data Index: 625366 (C4 (Web Text))

Max Activating Token Index: 963

Text #19

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0497. Min Act: -0.0002

Data Index: 400450 (C4 (Web Text))

Max Activating Token Index: 344