Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1993 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.1052. Min Act: -0.0002

Data Index: 1125680 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0989. Min Act: -0.0002

Data Index: 255959 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.1001. Min Act: -0.0002

Data Index: 1207206 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0981. Min Act: -0.0002

Data Index: 168837 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0977. Min Act: -0.0002

Data Index: 189762 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0991. Min Act: -0.0002

Data Index: 1020793 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0965. Min Act: -0.0002

Data Index: 1191272 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0957. Min Act: -0.0002

Data Index: 750403 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0926. Min Act: -0.0002

Data Index: 520953 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0888. Min Act: -0.0002

Data Index: 490905 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0899. Min Act: -0.0002

Data Index: 358110 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0879. Min Act: -0.0002

Data Index: 830584 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0910. Min Act: -0.0002

Data Index: 566562 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0898. Min Act: -0.0002

Data Index: 350578 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0878. Min Act: -0.0002

Data Index: 573007 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0854. Min Act: -0.0002

Data Index: 663419 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0815. Min Act: -0.0002

Data Index: 228897 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0836. Min Act: -0.0002

Data Index: 600639 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0847. Min Act: -0.0002

Data Index: 201268 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0835. Min Act: -0.0002

Data Index: 1266390 (C4 (Web Text))

Max Activating Token Index: 105