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

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

Neuron 1908 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: 0.0876. Min Range: -0.0876

Max Act: 0.0876. Min Act: -0.0003

Data Index: 505816 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0796. Min Act: -0.0003

Data Index: 9636 (C4 (Web Text))

Max Activating Token Index: 332

Text #2

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0687. Min Act: -0.0003

Data Index: 698848 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0671. Min Act: -0.0003

Data Index: 708254 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0699. Min Act: -0.0003

Data Index: 612223 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0653. Min Act: -0.0003

Data Index: 891088 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0660. Min Act: -0.0003

Data Index: 838765 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0647. Min Act: -0.0003

Data Index: 529366 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0611. Min Act: -0.0003

Data Index: 975526 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0674. Min Act: -0.0003

Data Index: 536854 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0622. Min Act: -0.0003

Data Index: 533822 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0618. Min Act: -0.0003

Data Index: 1224110 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0589. Min Act: -0.0003

Data Index: 51845 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0581. Min Act: -0.0003

Data Index: 1255322 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0602. Min Act: -0.0003

Data Index: 240335 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0595. Min Act: -0.0003

Data Index: 534923 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0593. Min Act: -0.0003

Data Index: 39581 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0594. Min Act: -0.0003

Data Index: 1130269 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0562. Min Act: -0.0003

Data Index: 244297 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0579. Min Act: -0.0003

Data Index: 649121 (C4 (Web Text))

Max Activating Token Index: 364