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

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

Neuron 2516 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.3323. Min Act: -0.0000

Data Index: 721222 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.3053. Min Act: -0.0000

Data Index: 1010952 (C4 (Web Text))

Max Activating Token Index: 485

Text #2

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.3011. Min Act: -0.0000

Data Index: 682608 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.3111. Min Act: -0.0000

Data Index: 1046431 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2824. Min Act: -0.0000

Data Index: 174307 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2722. Min Act: -0.0000

Data Index: 630906 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2657. Min Act: -0.0000

Data Index: 658191 (C4 (Web Text))

Max Activating Token Index: 877

Text #7

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2818. Min Act: -0.0000

Data Index: 869763 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2714. Min Act: -0.0000

Data Index: 818102 (C4 (Web Text))

Max Activating Token Index: 1018

Text #9

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2681. Min Act: -0.0000

Data Index: 554717 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2777. Min Act: -0.0000

Data Index: 149296 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2764. Min Act: -0.0000

Data Index: 578988 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2759. Min Act: -0.0000

Data Index: 256685 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2639. Min Act: -0.0000

Data Index: 972261 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2618. Min Act: -0.0000

Data Index: 150419 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2518. Min Act: -0.0000

Data Index: 906988 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2588. Min Act: -0.0000

Data Index: 461281 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2403. Min Act: -0.0000

Data Index: 445944 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2468. Min Act: -0.0000

Data Index: 636200 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2461. Min Act: -0.0000

Data Index: 685013 (C4 (Web Text))

Max Activating Token Index: 901