Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5222 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0008. Min Act: -0.0002

Data Index: 844787 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0008. Min Act: -0.0002

Data Index: 685036 (C4 (Web Text))

Max Activating Token Index: 1009

Text #2

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0007. Min Act: -0.0002

Data Index: 925383 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0007. Min Act: -0.0002

Data Index: 372581 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0007. Min Act: -0.0002

Data Index: 148767 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0006. Min Act: -0.0002

Data Index: 1086647 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0006. Min Act: -0.0002

Data Index: 197737 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0006. Min Act: -0.0002

Data Index: 978410 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0006. Min Act: -0.0002

Data Index: 279231 (C4 (Web Text))

Max Activating Token Index: 1010

Text #9

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0006. Min Act: -0.0002

Data Index: 537748 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0006. Min Act: -0.0002

Data Index: 1243680 (C4 (Web Text))

Max Activating Token Index: 1016

Text #11

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0005. Min Act: -0.0002

Data Index: 266013 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0005. Min Act: -0.0002

Data Index: 27936 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0005. Min Act: -0.0002

Data Index: 318009 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0005. Min Act: -0.0002

Data Index: 674459 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0005. Min Act: -0.0002

Data Index: 1205272 (C4 (Web Text))

Max Activating Token Index: 1022

Text #16

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0005. Min Act: -0.0002

Data Index: 326084 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0005. Min Act: -0.0002

Data Index: 819571 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0005. Min Act: -0.0002

Data Index: 886380 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0005. Min Act: -0.0002

Data Index: 226085 (C4 (Web Text))

Max Activating Token Index: 1013