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

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

Neuron 563 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0761. Min Act: -0.0002

Data Index: 473014 (C4 (Web Text))

Max Activating Token Index: 777

Text #1

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0726. Min Act: -0.0001

Data Index: 680378 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0671. Min Act: -0.0002

Data Index: 1335221 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0652. Min Act: -0.0002

Data Index: 488838 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0599. Min Act: -0.0002

Data Index: 1230067 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0624. Min Act: -0.0002

Data Index: 376159 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0621. Min Act: -0.0002

Data Index: 830378 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0699. Min Act: -0.0001

Data Index: 1576474 (Python Code)

Max Activating Token Index: 594

Text #8

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0578. Min Act: -0.0002

Data Index: 753497 (C4 (Web Text))

Max Activating Token Index: 474

Text #9

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0573. Min Act: -0.0001

Data Index: 414190 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0617. Min Act: -0.0001

Data Index: 1144584 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0590. Min Act: -0.0001

Data Index: 423630 (C4 (Web Text))

Max Activating Token Index: 972

Text #12

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0558. Min Act: -0.0001

Data Index: 1491448 (Python Code)

Max Activating Token Index: 637

Text #13

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0553. Min Act: -0.0001

Data Index: 229644 (C4 (Web Text))

Max Activating Token Index: 553

Text #14

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0591. Min Act: -0.0001

Data Index: 1159019 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0544. Min Act: -0.0001

Data Index: 442934 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0500. Min Act: -0.0001

Data Index: 378161 (C4 (Web Text))

Max Activating Token Index: 658

Text #17

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0571. Min Act: -0.0001

Data Index: 1175812 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0523. Min Act: -0.0002

Data Index: 955946 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0544. Min Act: -0.0001

Data Index: 163752 (C4 (Web Text))

Max Activating Token Index: 496