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

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

Neuron 1521 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0642. Min Act: -0.0001

Data Index: 954955 (C4 (Web Text))

Max Activating Token Index: 622

Text #1

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0551. Min Act: -0.0001

Data Index: 244207 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0556. Min Act: -0.0001

Data Index: 680764 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0526. Min Act: -0.0001

Data Index: 1062837 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0490. Min Act: -0.0001

Data Index: 1269406 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0499. Min Act: -0.0001

Data Index: 1013983 (C4 (Web Text))

Max Activating Token Index: 935

Text #6

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0488. Min Act: -0.0001

Data Index: 1412810 (Python Code)

Max Activating Token Index: 666

Text #7

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0477. Min Act: -0.0001

Data Index: 536200 (C4 (Web Text))

Max Activating Token Index: 958

Text #8

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0483. Min Act: -0.0001

Data Index: 605437 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0450. Min Act: -0.0001

Data Index: 1475355 (Python Code)

Max Activating Token Index: 392

Text #10

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0456. Min Act: -0.0001

Data Index: 635861 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0456. Min Act: -0.0001

Data Index: 1349650 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0450. Min Act: -0.0001

Data Index: 431625 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0423. Min Act: -0.0001

Data Index: 1544050 (Python Code)

Max Activating Token Index: 768

Text #14

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0440. Min Act: -0.0001

Data Index: 873339 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0453. Min Act: -0.0001

Data Index: 1495295 (Python Code)

Max Activating Token Index: 1009

Text #16

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0454. Min Act: -0.0001

Data Index: 1619963 (Python Code)

Max Activating Token Index: 470

Text #17

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0404. Min Act: -0.0001

Data Index: 820632 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0434. Min Act: -0.0001

Data Index: 490613 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0432. Min Act: -0.0001

Data Index: 1422468 (Python Code)

Max Activating Token Index: 419