Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1814 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0901. Min Act: -0.0002

Data Index: 1471641 (Python Code)

Max Activating Token Index: 112

Text #1

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0919. Min Act: -0.0002

Data Index: 432704 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0870. Min Act: -0.0002

Data Index: 887701 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0821. Min Act: -0.0002

Data Index: 64597 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0848. Min Act: -0.0002

Data Index: 109820 (C4 (Web Text))

Max Activating Token Index: 603

Text #5

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0845. Min Act: -0.0002

Data Index: 245600 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0843. Min Act: -0.0002

Data Index: 497935 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0825. Min Act: -0.0002

Data Index: 803378 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0847. Min Act: -0.0002

Data Index: 1290690 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0816. Min Act: -0.0002

Data Index: 287277 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0795. Min Act: -0.0002

Data Index: 1180449 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0764. Min Act: -0.0002

Data Index: 1282275 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0786. Min Act: -0.0002

Data Index: 73718 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0780. Min Act: -0.0002

Data Index: 623962 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0757. Min Act: -0.0002

Data Index: 683257 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0752. Min Act: -0.0002

Data Index: 968934 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0747. Min Act: -0.0002

Data Index: 1408769 (Python Code)

Max Activating Token Index: 461

Text #17

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0772. Min Act: -0.0002

Data Index: 548810 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0741. Min Act: -0.0002

Data Index: 861419 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0743. Min Act: -0.0002

Data Index: 739913 (C4 (Web Text))

Max Activating Token Index: 94