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

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

Neuron 1734 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1225. Min Act: -0.0001

Data Index: 208657 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1209. Min Act: -0.0001

Data Index: 555631 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1149. Min Act: -0.0001

Data Index: 673802 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1080. Min Act: -0.0001

Data Index: 650541 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1050. Min Act: -0.0001

Data Index: 423173 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1127. Min Act: -0.0001

Data Index: 681152 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1075. Min Act: -0.0001

Data Index: 894615 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1034. Min Act: -0.0001

Data Index: 1309714 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1060. Min Act: -0.0001

Data Index: 576141 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1047. Min Act: -0.0001

Data Index: 1066902 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1073. Min Act: -0.0001

Data Index: 1212490 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1131. Min Act: -0.0001

Data Index: 349706 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1150. Min Act: -0.0001

Data Index: 16341 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1016. Min Act: -0.0001

Data Index: 445835 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0999. Min Act: -0.0001

Data Index: 193835 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1077. Min Act: -0.0001

Data Index: 881320 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1021. Min Act: -0.0001

Data Index: 1118390 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1027. Min Act: -0.0001

Data Index: 3943 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1054. Min Act: -0.0001

Data Index: 389270 (C4 (Web Text))

Max Activating Token Index: 234

Text #19

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1024. Min Act: -0.0001

Data Index: 668800 (C4 (Web Text))

Max Activating Token Index: 773