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

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

Neuron 420 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: 1.0984. Min Range: -1.0984

Max Act: 1.0984. Min Act: -0.0000

Data Index: 23562 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 1.0984. Min Range: -1.0984

Max Act: 1.0636. Min Act: -0.0000

Data Index: 1031579 (C4 (Web Text))

Max Activating Token Index: 879

Text #2

Max Range: 1.0984. Min Range: -1.0984

Max Act: 1.0887. Min Act: -0.0000

Data Index: 1088767 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 1.0984. Min Range: -1.0984

Max Act: 1.0583. Min Act: -0.0001

Data Index: 364934 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 1.0984. Min Range: -1.0984

Max Act: 1.0656. Min Act: -0.0000

Data Index: 832746 (C4 (Web Text))

Max Activating Token Index: 774

Text #5

Max Range: 1.0984. Min Range: -1.0984

Max Act: 1.0893. Min Act: -0.0000

Data Index: 1041264 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 1.0984. Min Range: -1.0984

Max Act: 1.0703. Min Act: -0.0000

Data Index: 431869 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 1.0984. Min Range: -1.0984

Max Act: 1.0133. Min Act: -0.0000

Data Index: 665295 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9758. Min Act: -0.0000

Data Index: 693091 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9702. Min Act: -0.0000

Data Index: 897033 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 1.0984. Min Range: -1.0984

Max Act: 1.0330. Min Act: -0.0000

Data Index: 718456 (C4 (Web Text))

Max Activating Token Index: 276

Text #11

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8947. Min Act: -0.0001

Data Index: 1587975 (Python Code)

Max Activating Token Index: 788

Text #12

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9442. Min Act: -0.0000

Data Index: 192086 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9728. Min Act: -0.0000

Data Index: 1039118 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 1.0984. Min Range: -1.0984

Max Act: 1.0247. Min Act: -0.0000

Data Index: 459411 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9211. Min Act: -0.0001

Data Index: 802099 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9518. Min Act: -0.0001

Data Index: 940842 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9890. Min Act: -0.0000

Data Index: 882646 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9793. Min Act: -0.0000

Data Index: 587312 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9520. Min Act: -0.0000

Data Index: 1180922 (C4 (Web Text))

Max Activating Token Index: 35