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

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

Neuron 2585 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1689. Min Act: -0.0000

Data Index: 752334 (C4 (Web Text))

Max Activating Token Index: 834

Text #1

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1201. Min Act: -0.0000

Data Index: 1187433 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1216. Min Act: -0.0000

Data Index: 148453 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.0964. Min Act: -0.0000

Data Index: 225288 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.0947. Min Act: -0.0000

Data Index: 619763 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.0957. Min Act: -0.0001

Data Index: 546999 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.0906. Min Act: -0.0000

Data Index: 760674 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.0877. Min Act: -0.0001

Data Index: 663329 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.0645. Min Act: -0.0000

Data Index: 748891 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.0833. Min Act: -0.0000

Data Index: 640944 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.0860. Min Act: -0.0000

Data Index: 712413 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.0752. Min Act: -0.0000

Data Index: 67477 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.0672. Min Act: -0.0000

Data Index: 1021488 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.0718. Min Act: -0.0000

Data Index: 764302 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.0775. Min Act: -0.0000

Data Index: 1077664 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.0978. Min Act: -0.0000

Data Index: 406640 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.0726. Min Act: -0.0000

Data Index: 997792 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.0760. Min Act: -0.0001

Data Index: 38618 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.0794. Min Act: -0.0000

Data Index: 220356 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.0711. Min Act: -0.0000

Data Index: 222576 (C4 (Web Text))

Max Activating Token Index: 989