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

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

Neuron 4833 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: 0.0807. Min Range: -0.0807

Max Act: 0.0759. Min Act: -0.0002

Data Index: 449626 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0800. Min Act: -0.0002

Data Index: 150032 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0807. Min Act: -0.0002

Data Index: 484237 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0748. Min Act: -0.0002

Data Index: 425447 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0670. Min Act: -0.0002

Data Index: 282143 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0694. Min Act: -0.0002

Data Index: 967028 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0715. Min Act: -0.0002

Data Index: 575541 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0663. Min Act: -0.0002

Data Index: 162514 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0685. Min Act: -0.0002

Data Index: 247314 (C4 (Web Text))

Max Activating Token Index: 1011

Text #9

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0633. Min Act: -0.0002

Data Index: 97354 (C4 (Web Text))

Max Activating Token Index: 356

Text #10

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0649. Min Act: -0.0002

Data Index: 978297 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0627. Min Act: -0.0002

Data Index: 838348 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0616. Min Act: -0.0002

Data Index: 682864 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0609. Min Act: -0.0002

Data Index: 480342 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0608. Min Act: -0.0002

Data Index: 1224543 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0595. Min Act: -0.0002

Data Index: 1350188 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0650. Min Act: -0.0002

Data Index: 944013 (C4 (Web Text))

Max Activating Token Index: 817

Text #17

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0571. Min Act: -0.0002

Data Index: 1194331 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0586. Min Act: -0.0002

Data Index: 1035951 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0542. Min Act: -0.0002

Data Index: 774902 (C4 (Web Text))

Max Activating Token Index: 75