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

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

Neuron 774 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.4526. Min Act: -0.0000

Data Index: 1437944 (Python Code)

Max Activating Token Index: 528

Text #1

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.3921. Min Act: -0.0000

Data Index: 1568270 (Python Code)

Max Activating Token Index: 806

Text #2

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.3375. Min Act: -0.0000

Data Index: 1476674 (Python Code)

Max Activating Token Index: 681

Text #3

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.3552. Min Act: -0.0000

Data Index: 1505701 (Python Code)

Max Activating Token Index: 387

Text #4

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.3556. Min Act: -0.0000

Data Index: 1004797 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.3042. Min Act: -0.0000

Data Index: 1113607 (C4 (Web Text))

Max Activating Token Index: 993

Text #6

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.3129. Min Act: -0.0000

Data Index: 1494661 (Python Code)

Max Activating Token Index: 454

Text #7

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.3323. Min Act: -0.0000

Data Index: 1251887 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.2907. Min Act: -0.0000

Data Index: 1054889 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.3023. Min Act: -0.0000

Data Index: 1630669 (Python Code)

Max Activating Token Index: 667

Text #10

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.2443. Min Act: -0.0000

Data Index: 1562694 (Python Code)

Max Activating Token Index: 710

Text #11

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.2802. Min Act: -0.0000

Data Index: 1402060 (Python Code)

Max Activating Token Index: 752

Text #12

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.2759. Min Act: -0.0000

Data Index: 1501121 (Python Code)

Max Activating Token Index: 967

Text #13

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.2551. Min Act: -0.0000

Data Index: 1570426 (Python Code)

Max Activating Token Index: 756

Text #14

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.2746. Min Act: -0.0000

Data Index: 1611672 (Python Code)

Max Activating Token Index: 988

Text #15

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.2653. Min Act: -0.0000

Data Index: 1311824 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.2644. Min Act: -0.0000

Data Index: 1200692 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.2527. Min Act: -0.0000

Data Index: 1372515 (Python Code)

Max Activating Token Index: 575

Text #18

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.2598. Min Act: -0.0000

Data Index: 1045450 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 0.4526. Min Range: -0.4526

Max Act: 0.2753. Min Act: -0.0000

Data Index: 191097 (C4 (Web Text))

Max Activating Token Index: 282