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

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

Neuron 782 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: 0.0068. Min Range: -0.0068

Max Act: 0.0067. Min Act: -0.0004

Data Index: 1481901 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0068. Min Act: -0.0005

Data Index: 823174 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0066. Min Act: -0.0005

Data Index: 561654 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0065. Min Act: -0.0005

Data Index: 364631 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0065. Min Act: -0.0005

Data Index: 1072077 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0065. Min Act: -0.0005

Data Index: 1293372 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0064. Min Act: -0.0005

Data Index: 930542 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0063. Min Act: -0.0004

Data Index: 1614593 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0063. Min Act: -0.0005

Data Index: 248517 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0063. Min Act: -0.0006

Data Index: 1255589 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0062. Min Act: -0.0005

Data Index: 875106 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0063. Min Act: -0.0005

Data Index: 857197 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0062. Min Act: -0.0006

Data Index: 1393675 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0063. Min Act: -0.0005

Data Index: 1498241 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0062. Min Act: -0.0005

Data Index: 632096 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0062. Min Act: -0.0005

Data Index: 1214285 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0061. Min Act: -0.0005

Data Index: 867523 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0061. Min Act: -0.0005

Data Index: 1591293 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0060. Min Act: -0.0005

Data Index: 657840 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0061. Min Act: -0.0005

Data Index: 415630 (C4 (Web Text))

Max Activating Token Index: 1023