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

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

Neuron 4040 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.1060. Min Act: -0.0001

Data Index: 488636 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.1054. Min Act: -0.0001

Data Index: 827022 (C4 (Web Text))

Max Activating Token Index: 1018

Text #2

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.1025. Min Act: -0.0001

Data Index: 308192 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0996. Min Act: -0.0001

Data Index: 436821 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0975. Min Act: -0.0001

Data Index: 1332327 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0961. Min Act: -0.0001

Data Index: 961948 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0967. Min Act: -0.0001

Data Index: 977825 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0998. Min Act: -0.0001

Data Index: 551682 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0926. Min Act: -0.0001

Data Index: 26502 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0865. Min Act: -0.0001

Data Index: 726123 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0958. Min Act: -0.0001

Data Index: 474962 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0976. Min Act: -0.0001

Data Index: 107341 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0910. Min Act: -0.0001

Data Index: 1288074 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0925. Min Act: -0.0001

Data Index: 90098 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.1000. Min Act: -0.0001

Data Index: 1175112 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0983. Min Act: -0.0001

Data Index: 855988 (C4 (Web Text))

Max Activating Token Index: 811

Text #16

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0948. Min Act: -0.0001

Data Index: 995532 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0927. Min Act: -0.0001

Data Index: 152890 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0940. Min Act: -0.0000

Data Index: 1268475 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0945. Min Act: -0.0001

Data Index: 357627 (C4 (Web Text))

Max Activating Token Index: 432