Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2751 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0730. Min Act: -0.0003

Data Index: 990326 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0741. Min Act: -0.0003

Data Index: 783405 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0664. Min Act: -0.0003

Data Index: 743088 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0659. Min Act: -0.0003

Data Index: 1150052 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0680. Min Act: -0.0003

Data Index: 579791 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0669. Min Act: -0.0003

Data Index: 1092175 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0664. Min Act: -0.0003

Data Index: 46293 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0637. Min Act: -0.0003

Data Index: 1192793 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0631. Min Act: -0.0003

Data Index: 933759 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0601. Min Act: -0.0003

Data Index: 460679 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0636. Min Act: -0.0003

Data Index: 256384 (C4 (Web Text))

Max Activating Token Index: 458

Text #11

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0565. Min Act: -0.0003

Data Index: 86554 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0617. Min Act: -0.0003

Data Index: 700855 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0644. Min Act: -0.0003

Data Index: 8683 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0578. Min Act: -0.0003

Data Index: 808120 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0616. Min Act: -0.0003

Data Index: 953465 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0593. Min Act: -0.0003

Data Index: 282329 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0578. Min Act: -0.0003

Data Index: 1107598 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0587. Min Act: -0.0003

Data Index: 17421 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0606. Min Act: -0.0003

Data Index: 1229237 (C4 (Web Text))

Max Activating Token Index: 902