Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4065 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1285. Min Act: -0.0002

Data Index: 482562 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1178. Min Act: -0.0002

Data Index: 60808 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1173. Min Act: -0.0002

Data Index: 1348825 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1155. Min Act: -0.0002

Data Index: 1045232 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1004. Min Act: -0.0002

Data Index: 1111654 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1017. Min Act: -0.0002

Data Index: 615957 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1112. Min Act: -0.0002

Data Index: 109487 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0996. Min Act: -0.0002

Data Index: 342472 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1067. Min Act: -0.0002

Data Index: 134027 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0993. Min Act: -0.0002

Data Index: 912776 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1014. Min Act: -0.0002

Data Index: 1279202 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0989. Min Act: -0.0002

Data Index: 1306024 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1005. Min Act: -0.0002

Data Index: 218998 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0997. Min Act: -0.0002

Data Index: 211617 (C4 (Web Text))

Max Activating Token Index: 773

Text #14

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1034. Min Act: -0.0002

Data Index: 399777 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0965. Min Act: -0.0002

Data Index: 948712 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0917. Min Act: -0.0002

Data Index: 9455 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1028. Min Act: -0.0002

Data Index: 65329 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0988. Min Act: -0.0002

Data Index: 440058 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0940. Min Act: -0.0002

Data Index: 326619 (C4 (Web Text))

Max Activating Token Index: 673