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

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

Neuron 2991 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.3403. Min Act: -0.0001

Data Index: 55389 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.3506. Min Act: -0.0000

Data Index: 888802 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.3268. Min Act: -0.0001

Data Index: 166723 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.3015. Min Act: 0.0000

Data Index: 1039542 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.2886. Min Act: -0.0001

Data Index: 772466 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.2744. Min Act: -0.0000

Data Index: 868386 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.2821. Min Act: -0.0001

Data Index: 870325 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.3006. Min Act: -0.0001

Data Index: 940498 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.2858. Min Act: 0.0000

Data Index: 284829 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.2905. Min Act: -0.0001

Data Index: 1039952 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.2807. Min Act: -0.0001

Data Index: 67441 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.2730. Min Act: -0.0001

Data Index: 82740 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.2799. Min Act: -0.0001

Data Index: 520722 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.2725. Min Act: -0.0001

Data Index: 1306748 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.2688. Min Act: -0.0001

Data Index: 1194593 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.2643. Min Act: -0.0001

Data Index: 280631 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.2588. Min Act: 0.0000

Data Index: 1340243 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.2474. Min Act: -0.0001

Data Index: 1009964 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.2565. Min Act: -0.0001

Data Index: 580388 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 0.3506. Min Range: -0.3506

Max Act: 0.2595. Min Act: -0.0001

Data Index: 1312568 (C4 (Web Text))

Max Activating Token Index: 361