Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1927 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0060. Min Act: -0.0006

Data Index: 889134 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0054. Min Act: -0.0006

Data Index: 1028947 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0055. Min Act: -0.0006

Data Index: 766943 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0052. Min Act: -0.0006

Data Index: 704026 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0052. Min Act: -0.0006

Data Index: 375234 (C4 (Web Text))

Max Activating Token Index: 856

Text #5

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0051. Min Act: -0.0006

Data Index: 1030370 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0053. Min Act: -0.0006

Data Index: 771504 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0051. Min Act: -0.0006

Data Index: 1254446 (C4 (Web Text))

Max Activating Token Index: 565

Text #8

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0052. Min Act: -0.0006

Data Index: 81015 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0050. Min Act: -0.0004

Data Index: 856463 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0050. Min Act: -0.0006

Data Index: 971215 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0051. Min Act: -0.0006

Data Index: 1019254 (C4 (Web Text))

Max Activating Token Index: 983

Text #12

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0050. Min Act: -0.0005

Data Index: 53988 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0044. Min Act: -0.0005

Data Index: 353065 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0048. Min Act: -0.0005

Data Index: 701059 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0048. Min Act: -0.0005

Data Index: 233968 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0047. Min Act: -0.0005

Data Index: 545932 (C4 (Web Text))

Max Activating Token Index: 781

Text #17

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0049. Min Act: -0.0006

Data Index: 423859 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0038. Min Act: -0.0006

Data Index: 873388 (C4 (Web Text))

Max Activating Token Index: 687

Text #19

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0047. Min Act: -0.0005

Data Index: 1589658 (Python Code)

Max Activating Token Index: 992