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

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

Neuron 1920 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1554. Min Act: -0.0001

Data Index: 452749 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1118. Min Act: -0.0001

Data Index: 66834 (C4 (Web Text))

Max Activating Token Index: 1010

Text #2

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1042. Min Act: -0.0001

Data Index: 485235 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1072. Min Act: -0.0001

Data Index: 884867 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1007. Min Act: -0.0001

Data Index: 505644 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.0995. Min Act: -0.0001

Data Index: 1038929 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1026. Min Act: -0.0001

Data Index: 333064 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.0965. Min Act: -0.0001

Data Index: 1210821 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.0938. Min Act: -0.0001

Data Index: 1173084 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.0970. Min Act: -0.0001

Data Index: 141747 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1008. Min Act: -0.0001

Data Index: 352245 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.0996. Min Act: -0.0001

Data Index: 1277685 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.0992. Min Act: -0.0001

Data Index: 26779 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.0984. Min Act: -0.0001

Data Index: 87616 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.0908. Min Act: -0.0001

Data Index: 937554 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1025. Min Act: -0.0001

Data Index: 294157 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.0932. Min Act: -0.0001

Data Index: 340066 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.0919. Min Act: -0.0001

Data Index: 879079 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.0965. Min Act: -0.0001

Data Index: 179954 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.0996. Min Act: -0.0001

Data Index: 1266328 (C4 (Web Text))

Max Activating Token Index: 226