Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1688 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.3713. Min Act: -0.0000

Data Index: 217491 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.3127. Min Act: -0.0000

Data Index: 8626 (C4 (Web Text))

Max Activating Token Index: 744

Text #2

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2956. Min Act: -0.0000

Data Index: 903345 (C4 (Web Text))

Max Activating Token Index: 604

Text #3

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2891. Min Act: -0.0000

Data Index: 681847 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2841. Min Act: -0.0001

Data Index: 1226786 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2699. Min Act: -0.0000

Data Index: 566661 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2776. Min Act: -0.0000

Data Index: 41240 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2759. Min Act: -0.0000

Data Index: 1204993 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2813. Min Act: -0.0000

Data Index: 327446 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2610. Min Act: -0.0001

Data Index: 1157765 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2657. Min Act: -0.0000

Data Index: 796412 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2639. Min Act: -0.0000

Data Index: 259153 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2614. Min Act: -0.0001

Data Index: 616262 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2712. Min Act: -0.0000

Data Index: 1098493 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2582. Min Act: -0.0000

Data Index: 406678 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2487. Min Act: -0.0001

Data Index: 1162395 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2558. Min Act: -0.0000

Data Index: 227858 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2614. Min Act: -0.0001

Data Index: 975089 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2538. Min Act: -0.0000

Data Index: 813895 (C4 (Web Text))

Max Activating Token Index: 752

Text #19

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2407. Min Act: -0.0000

Data Index: 1333389 (C4 (Web Text))

Max Activating Token Index: 590