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

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

Neuron 524 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: 0.0879. Min Range: -0.0879

Max Act: 0.0879. Min Act: -0.0002

Data Index: 1122924 (C4 (Web Text))

Max Activating Token Index: 623

Text #1

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0803. Min Act: -0.0002

Data Index: 999863 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0782. Min Act: -0.0002

Data Index: 1248533 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0723. Min Act: -0.0002

Data Index: 159009 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0684. Min Act: -0.0002

Data Index: 959766 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0622. Min Act: -0.0002

Data Index: 735036 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0707. Min Act: -0.0002

Data Index: 615362 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0701. Min Act: -0.0002

Data Index: 861701 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0667. Min Act: -0.0002

Data Index: 1233455 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0649. Min Act: -0.0002

Data Index: 832269 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0624. Min Act: -0.0002

Data Index: 1296547 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0618. Min Act: -0.0002

Data Index: 1247466 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0615. Min Act: -0.0002

Data Index: 1160115 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0577. Min Act: -0.0002

Data Index: 90285 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1286095 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0577. Min Act: -0.0002

Data Index: 665869 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0571. Min Act: -0.0002

Data Index: 262853 (C4 (Web Text))

Max Activating Token Index: 992

Text #17

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0585. Min Act: -0.0002

Data Index: 730496 (C4 (Web Text))

Max Activating Token Index: 945

Text #18

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0573. Min Act: -0.0002

Data Index: 297288 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0587. Min Act: -0.0002

Data Index: 219726 (C4 (Web Text))

Max Activating Token Index: 577