Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 505 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0930. Min Act: -0.0002

Data Index: 392156 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0779. Min Act: -0.0002

Data Index: 976942 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0728. Min Act: -0.0002

Data Index: 374779 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0752. Min Act: -0.0002

Data Index: 1014907 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0793. Min Act: -0.0002

Data Index: 1147832 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0696. Min Act: -0.0002

Data Index: 533832 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0659. Min Act: -0.0002

Data Index: 1182346 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0742. Min Act: -0.0002

Data Index: 1061046 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0665. Min Act: -0.0002

Data Index: 95651 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0686. Min Act: -0.0002

Data Index: 153539 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0658. Min Act: -0.0002

Data Index: 1043425 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0682. Min Act: -0.0002

Data Index: 301638 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0656. Min Act: -0.0002

Data Index: 1357515 (C4 (Web Text))

Max Activating Token Index: 187

Text #13

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0675. Min Act: -0.0002

Data Index: 306888 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0689. Min Act: -0.0002

Data Index: 968328 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0656. Min Act: -0.0002

Data Index: 429981 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0680. Min Act: -0.0002

Data Index: 1060484 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0669. Min Act: -0.0002

Data Index: 799450 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0621. Min Act: -0.0002

Data Index: 282225 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0678. Min Act: -0.0002

Data Index: 1126513 (C4 (Web Text))

Max Activating Token Index: 512