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

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

Neuron 1215 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: 0.0008. Min Range: -0.0008

Max Act: 0.0007. Min Act: -0.0004

Data Index: 585830 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0008. Min Act: -0.0004

Data Index: 22354 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0006. Min Act: -0.0004

Data Index: 369372 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0005. Min Act: -0.0004

Data Index: 959147 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0005. Min Act: -0.0004

Data Index: 743774 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0005. Min Act: -0.0004

Data Index: 1346640 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0004. Min Act: -0.0004

Data Index: 833617 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0004. Min Act: -0.0004

Data Index: 76960 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0004. Min Act: -0.0004

Data Index: 143155 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0004. Min Act: -0.0004

Data Index: 488530 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0003. Min Act: -0.0004

Data Index: 228317 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0004. Min Act: -0.0004

Data Index: 1048065 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0004. Min Act: -0.0005

Data Index: 311355 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0003. Min Act: -0.0004

Data Index: 265747 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0003. Min Act: -0.0004

Data Index: 243201 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0003. Min Act: -0.0004

Data Index: 605131 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0003. Min Act: -0.0005

Data Index: 473784 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0003. Min Act: -0.0004

Data Index: 637814 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0004. Min Act: -0.0005

Data Index: 407951 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0003. Min Act: -0.0004

Data Index: 1324073 (C4 (Web Text))

Max Activating Token Index: 1023