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

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

Neuron 2780 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.1089. Min Act: -0.0004

Data Index: 667131 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.1061. Min Act: -0.0004

Data Index: 1004060 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.1058. Min Act: -0.0004

Data Index: 1335181 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.1053. Min Act: -0.0004

Data Index: 555024 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.1022. Min Act: -0.0004

Data Index: 1074771 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.1075. Min Act: -0.0004

Data Index: 497524 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0977. Min Act: -0.0004

Data Index: 124948 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.1013. Min Act: -0.0004

Data Index: 563963 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.1009. Min Act: -0.0004

Data Index: 875170 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0999. Min Act: -0.0004

Data Index: 450187 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0927. Min Act: -0.0004

Data Index: 1211640 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0987. Min Act: -0.0004

Data Index: 983999 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0944. Min Act: -0.0004

Data Index: 1035076 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0964. Min Act: -0.0004

Data Index: 634027 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.1018. Min Act: -0.0004

Data Index: 631902 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0966. Min Act: -0.0004

Data Index: 480753 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0892. Min Act: -0.0004

Data Index: 601693 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0926. Min Act: -0.0004

Data Index: 1063630 (C4 (Web Text))

Max Activating Token Index: 173

Text #18

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0997. Min Act: -0.0004

Data Index: 967641 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0921. Min Act: -0.0004

Data Index: 987369 (C4 (Web Text))

Max Activating Token Index: 364