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

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

Neuron 1516 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1302. Min Act: -0.0000

Data Index: 146058 (C4 (Web Text))

Max Activating Token Index: 358

Text #1

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1405. Min Act: -0.0000

Data Index: 637853 (C4 (Web Text))

Max Activating Token Index: 860

Text #2

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1018. Min Act: 0.0000

Data Index: 388818 (C4 (Web Text))

Max Activating Token Index: 966

Text #3

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.0776. Min Act: -0.0000

Data Index: 790232 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.0856. Min Act: -0.0001

Data Index: 1162336 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.0815. Min Act: -0.0001

Data Index: 746613 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.0868. Min Act: -0.0000

Data Index: 523951 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.0828. Min Act: 0.0000

Data Index: 736942 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.0817. Min Act: 0.0000

Data Index: 709061 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.0779. Min Act: 0.0000

Data Index: 670699 (C4 (Web Text))

Max Activating Token Index: 849

Text #10

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.0792. Min Act: -0.0000

Data Index: 1186429 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.0782. Min Act: -0.0000

Data Index: 518601 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.0710. Min Act: 0.0000

Data Index: 489957 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.0766. Min Act: -0.0001

Data Index: 1136190 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.0691. Min Act: -0.0000

Data Index: 1159477 (C4 (Web Text))

Max Activating Token Index: 479

Text #15

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.0644. Min Act: -0.0000

Data Index: 519075 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.0663. Min Act: -0.0001

Data Index: 13169 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.0716. Min Act: -0.0001

Data Index: 1450083 (Python Code)

Max Activating Token Index: 681

Text #18

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.0683. Min Act: 0.0000

Data Index: 249450 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.0747. Min Act: 0.0000

Data Index: 548541 (C4 (Web Text))

Max Activating Token Index: 603