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

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

Neuron 1782 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: 0.1274. Min Range: -0.1274

Max Act: 0.1273. Min Act: -0.0001

Data Index: 994124 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1274. Min Act: -0.0001

Data Index: 793422 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1198. Min Act: -0.0001

Data Index: 239104 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1086. Min Act: -0.0001

Data Index: 519136 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1128. Min Act: -0.0001

Data Index: 724969 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1146. Min Act: -0.0001

Data Index: 688363 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1137. Min Act: -0.0001

Data Index: 1258594 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1054. Min Act: -0.0001

Data Index: 8386 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1033. Min Act: -0.0001

Data Index: 805651 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1070. Min Act: -0.0001

Data Index: 197913 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1061. Min Act: -0.0001

Data Index: 1084589 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.0989. Min Act: -0.0001

Data Index: 27544 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1055. Min Act: -0.0001

Data Index: 300764 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.0974. Min Act: -0.0001

Data Index: 707179 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1006. Min Act: -0.0001

Data Index: 1177539 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.0966. Min Act: -0.0001

Data Index: 179698 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.0989. Min Act: -0.0001

Data Index: 639351 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.0985. Min Act: -0.0001

Data Index: 635920 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1019. Min Act: -0.0001

Data Index: 627890 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1023. Min Act: -0.0001

Data Index: 864040 (C4 (Web Text))

Max Activating Token Index: 997