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

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

Neuron 516 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: 0.1182. Min Range: -0.1182

Max Act: 0.1167. Min Act: -0.0002

Data Index: 863892 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1141. Min Act: -0.0002

Data Index: 953537 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1182. Min Act: -0.0002

Data Index: 27018 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1128. Min Act: -0.0002

Data Index: 988756 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1140. Min Act: -0.0002

Data Index: 124193 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1069. Min Act: -0.0002

Data Index: 822618 (C4 (Web Text))

Max Activating Token Index: 678

Text #6

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1063. Min Act: -0.0002

Data Index: 1272796 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1090. Min Act: -0.0002

Data Index: 892542 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1100. Min Act: -0.0002

Data Index: 417180 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1074. Min Act: -0.0002

Data Index: 499704 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1065. Min Act: -0.0002

Data Index: 259589 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1080. Min Act: -0.0002

Data Index: 852609 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1018. Min Act: -0.0002

Data Index: 1148511 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1046. Min Act: -0.0002

Data Index: 293593 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1005. Min Act: -0.0002

Data Index: 1050731 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1020. Min Act: -0.0002

Data Index: 25502 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1012. Min Act: -0.0002

Data Index: 277355 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1049. Min Act: -0.0002

Data Index: 749654 (C4 (Web Text))

Max Activating Token Index: 454

Text #18

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0966. Min Act: -0.0002

Data Index: 722165 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1006. Min Act: -0.0002

Data Index: 889065 (C4 (Web Text))

Max Activating Token Index: 745