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

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

Neuron 212 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.3069. Min Act: -0.0002

Data Index: 611907 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2911. Min Act: -0.0002

Data Index: 98854 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.3026. Min Act: -0.0002

Data Index: 464488 (C4 (Web Text))

Max Activating Token Index: 522

Text #3

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.3113. Min Act: -0.0002

Data Index: 307061 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2924. Min Act: -0.0002

Data Index: 383363 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2717. Min Act: -0.0002

Data Index: 1223712 (C4 (Web Text))

Max Activating Token Index: 875

Text #6

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2895. Min Act: -0.0002

Data Index: 1018756 (C4 (Web Text))

Max Activating Token Index: 690

Text #7

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2880. Min Act: -0.0002

Data Index: 228351 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2708. Min Act: -0.0002

Data Index: 1113997 (C4 (Web Text))

Max Activating Token Index: 709

Text #9

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2840. Min Act: -0.0002

Data Index: 464340 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2741. Min Act: -0.0002

Data Index: 1284419 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2697. Min Act: -0.0002

Data Index: 596278 (C4 (Web Text))

Max Activating Token Index: 772

Text #12

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2907. Min Act: -0.0002

Data Index: 719489 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2646. Min Act: -0.0002

Data Index: 798506 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2926. Min Act: -0.0002

Data Index: 404801 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2653. Min Act: -0.0002

Data Index: 153491 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2631. Min Act: -0.0002

Data Index: 695337 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2594. Min Act: -0.0002

Data Index: 628467 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2383. Min Act: -0.0002

Data Index: 621060 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2359. Min Act: -0.0002

Data Index: 602164 (C4 (Web Text))

Max Activating Token Index: 52