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

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

Neuron 29 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0073. Min Act: -0.0006

Data Index: 1276890 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0066. Min Act: -0.0006

Data Index: 700665 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0063. Min Act: -0.0006

Data Index: 63067 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0062. Min Act: -0.0006

Data Index: 805101 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0061. Min Act: -0.0006

Data Index: 395093 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0060. Min Act: -0.0005

Data Index: 802695 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0059. Min Act: -0.0006

Data Index: 29133 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0058. Min Act: -0.0006

Data Index: 207589 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0058. Min Act: -0.0005

Data Index: 617439 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0058. Min Act: -0.0006

Data Index: 1340435 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0057. Min Act: -0.0006

Data Index: 81796 (C4 (Web Text))

Max Activating Token Index: 865

Text #11

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0057. Min Act: -0.0006

Data Index: 467171 (C4 (Web Text))

Max Activating Token Index: 462

Text #12

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0056. Min Act: -0.0006

Data Index: 807007 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0056. Min Act: -0.0006

Data Index: 870957 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0056. Min Act: -0.0006

Data Index: 1056385 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0055. Min Act: -0.0006

Data Index: 1176222 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0056. Min Act: -0.0006

Data Index: 414559 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0055. Min Act: -0.0005

Data Index: 1580789 (Python Code)

Max Activating Token Index: 11

Text #18

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0054. Min Act: -0.0006

Data Index: 860594 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0055. Min Act: -0.0006

Data Index: 1146503 (C4 (Web Text))

Max Activating Token Index: 700