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

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

Neuron 1947 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: 1343559 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0056. Min Act: -0.0005

Data Index: 1177145 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0054. Min Act: -0.0005

Data Index: 994418 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0053. Min Act: -0.0005

Data Index: 1172738 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0052. Min Act: -0.0005

Data Index: 736935 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0052. Min Act: -0.0005

Data Index: 275249 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0051. Min Act: -0.0005

Data Index: 1072018 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0050. Min Act: -0.0005

Data Index: 164460 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0049. Min Act: -0.0005

Data Index: 331454 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0049. Min Act: -0.0005

Data Index: 634971 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0048. Min Act: -0.0005

Data Index: 446179 (C4 (Web Text))

Max Activating Token Index: 848

Text #11

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0048. Min Act: -0.0004

Data Index: 452932 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0048. Min Act: -0.0005

Data Index: 697040 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0048. Min Act: -0.0005

Data Index: 990633 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0048. Min Act: -0.0005

Data Index: 65332 (C4 (Web Text))

Max Activating Token Index: 765

Text #15

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0048. Min Act: -0.0005

Data Index: 702445 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0048. Min Act: -0.0005

Data Index: 1164077 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0048. Min Act: -0.0005

Data Index: 365564 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0049. Min Act: -0.0005

Data Index: 1072987 (C4 (Web Text))

Max Activating Token Index: 959

Text #19

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0048. Min Act: -0.0005

Data Index: 1292084 (C4 (Web Text))

Max Activating Token Index: 435