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

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

Neuron 3319 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0980. Min Act: -0.0002

Data Index: 627527 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0974. Min Act: -0.0002

Data Index: 1237795 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0963. Min Act: -0.0002

Data Index: 837981 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0956. Min Act: -0.0002

Data Index: 842221 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0981. Min Act: -0.0002

Data Index: 1203303 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0951. Min Act: -0.0002

Data Index: 1276037 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0944. Min Act: -0.0002

Data Index: 1187018 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0929. Min Act: -0.0002

Data Index: 730633 (C4 (Web Text))

Max Activating Token Index: 865

Text #8

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0936. Min Act: -0.0002

Data Index: 1189376 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0934. Min Act: -0.0002

Data Index: 218300 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0938. Min Act: -0.0002

Data Index: 47032 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0947. Min Act: -0.0002

Data Index: 1108873 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0931. Min Act: -0.0002

Data Index: 1297908 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0937. Min Act: -0.0002

Data Index: 431332 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0924. Min Act: -0.0002

Data Index: 1113780 (C4 (Web Text))

Max Activating Token Index: 721

Text #15

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0920. Min Act: -0.0002

Data Index: 159504 (C4 (Web Text))

Max Activating Token Index: 831

Text #16

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0917. Min Act: -0.0002

Data Index: 28509 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0903. Min Act: -0.0002

Data Index: 1057652 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0916. Min Act: -0.0002

Data Index: 1141128 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0904. Min Act: -0.0002

Data Index: 203904 (C4 (Web Text))

Max Activating Token Index: 913