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

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

Neuron 697 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0057. Min Act: -0.0005

Data Index: 34057 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0057. Min Act: -0.0005

Data Index: 1612868 (Python Code)

Max Activating Token Index: 898

Text #2

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0056. Min Act: -0.0005

Data Index: 119358 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0053. Min Act: -0.0005

Data Index: 504538 (C4 (Web Text))

Max Activating Token Index: 737

Text #4

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0052. Min Act: -0.0005

Data Index: 399590 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0053. Min Act: -0.0005

Data Index: 334882 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0052. Min Act: -0.0005

Data Index: 961733 (C4 (Web Text))

Max Activating Token Index: 905

Text #7

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0051. Min Act: -0.0005

Data Index: 1135466 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0052. Min Act: -0.0005

Data Index: 522656 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0052. Min Act: -0.0005

Data Index: 519312 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0051. Min Act: -0.0005

Data Index: 627642 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0050. Min Act: -0.0005

Data Index: 266270 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0048. Min Act: -0.0005

Data Index: 124554 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0048. Min Act: -0.0005

Data Index: 374710 (C4 (Web Text))

Max Activating Token Index: 972

Text #14

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0049. Min Act: -0.0005

Data Index: 599385 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0047. Min Act: -0.0005

Data Index: 523931 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0048. Min Act: -0.0005

Data Index: 984685 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0048. Min Act: -0.0005

Data Index: 307932 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0048. Min Act: -0.0005

Data Index: 765424 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0048. Min Act: -0.0005

Data Index: 187682 (C4 (Web Text))

Max Activating Token Index: 1023