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

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

Neuron 1036 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0884. Min Act: -0.0001

Data Index: 733463 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0853. Min Act: -0.0001

Data Index: 642096 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0849. Min Act: -0.0001

Data Index: 1053318 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0801. Min Act: -0.0001

Data Index: 175836 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0800. Min Act: -0.0001

Data Index: 1083996 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0761. Min Act: -0.0001

Data Index: 1035217 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0802. Min Act: -0.0001

Data Index: 103708 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0781. Min Act: -0.0001

Data Index: 454433 (C4 (Web Text))

Max Activating Token Index: 631

Text #8

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0779. Min Act: -0.0001

Data Index: 1029441 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0769. Min Act: -0.0001

Data Index: 726458 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0771. Min Act: -0.0001

Data Index: 1158626 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0782. Min Act: -0.0001

Data Index: 1317619 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0725. Min Act: -0.0001

Data Index: 1099070 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0751. Min Act: -0.0001

Data Index: 322587 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0742. Min Act: -0.0001

Data Index: 640313 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0752. Min Act: -0.0001

Data Index: 239934 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0774. Min Act: -0.0001

Data Index: 196404 (C4 (Web Text))

Max Activating Token Index: 500

Text #17

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0721. Min Act: -0.0001

Data Index: 1301272 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0754. Min Act: -0.0001

Data Index: 628806 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0719. Min Act: -0.0001

Data Index: 814382 (C4 (Web Text))

Max Activating Token Index: 271