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

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

Neuron 2687 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0851. Min Act: -0.0001

Data Index: 844332 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0831. Min Act: -0.0001

Data Index: 451007 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0831. Min Act: -0.0001

Data Index: 54686 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0762. Min Act: -0.0001

Data Index: 816781 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0760. Min Act: -0.0001

Data Index: 16747 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0732. Min Act: -0.0001

Data Index: 707701 (C4 (Web Text))

Max Activating Token Index: 539

Text #6

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0775. Min Act: -0.0001

Data Index: 231546 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0770. Min Act: -0.0001

Data Index: 877592 (C4 (Web Text))

Max Activating Token Index: 666

Text #8

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0722. Min Act: -0.0001

Data Index: 893335 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0616. Min Act: -0.0001

Data Index: 287013 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0775. Min Act: -0.0001

Data Index: 396487 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0635. Min Act: -0.0001

Data Index: 52912 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0733. Min Act: -0.0001

Data Index: 546191 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0758. Min Act: -0.0001

Data Index: 1333865 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0726. Min Act: -0.0001

Data Index: 1321076 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0716. Min Act: -0.0001

Data Index: 811036 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0727. Min Act: -0.0001

Data Index: 582976 (C4 (Web Text))

Max Activating Token Index: 878

Text #17

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0692. Min Act: -0.0001

Data Index: 620693 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0705. Min Act: -0.0001

Data Index: 76541 (C4 (Web Text))

Max Activating Token Index: 708

Text #19

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0683. Min Act: -0.0001

Data Index: 60627 (C4 (Web Text))

Max Activating Token Index: 536