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

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

Neuron 3892 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: 0.0935. Min Range: -0.0935

Max Act: 0.0836. Min Act: -0.0001

Data Index: 1217668 (C4 (Web Text))

Max Activating Token Index: 513

Text #1

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0935. Min Act: -0.0001

Data Index: 387649 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0869. Min Act: -0.0001

Data Index: 426349 (C4 (Web Text))

Max Activating Token Index: 708

Text #3

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0856. Min Act: -0.0001

Data Index: 160173 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0799. Min Act: -0.0001

Data Index: 1261597 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0871. Min Act: -0.0001

Data Index: 415362 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0778. Min Act: -0.0001

Data Index: 1189110 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0767. Min Act: -0.0001

Data Index: 491905 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0747. Min Act: -0.0001

Data Index: 930387 (C4 (Web Text))

Max Activating Token Index: 305

Text #9

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0722. Min Act: -0.0001

Data Index: 1238033 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0727. Min Act: -0.0001

Data Index: 620866 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0744. Min Act: -0.0001

Data Index: 424384 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0674. Min Act: -0.0001

Data Index: 1009467 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0696. Min Act: -0.0001

Data Index: 1269214 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0705. Min Act: -0.0001

Data Index: 350604 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0700. Min Act: -0.0001

Data Index: 730296 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0734. Min Act: -0.0001

Data Index: 950606 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0672. Min Act: -0.0001

Data Index: 1049717 (C4 (Web Text))

Max Activating Token Index: 678

Text #18

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0664. Min Act: -0.0001

Data Index: 1128582 (C4 (Web Text))

Max Activating Token Index: 1011

Text #19

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0689. Min Act: -0.0001

Data Index: 576575 (C4 (Web Text))

Max Activating Token Index: 208