Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2979 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0027. Min Act: -0.0004

Data Index: 525511 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0024. Min Act: -0.0004

Data Index: 749219 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0021. Min Act: -0.0004

Data Index: 1037243 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0020. Min Act: -0.0004

Data Index: 695985 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0019. Min Act: -0.0004

Data Index: 51723 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0018. Min Act: -0.0004

Data Index: 367862 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0018. Min Act: -0.0004

Data Index: 121010 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0017. Min Act: -0.0004

Data Index: 672602 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0018. Min Act: -0.0004

Data Index: 565732 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0017. Min Act: -0.0004

Data Index: 1248720 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0016. Min Act: -0.0004

Data Index: 824416 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0017. Min Act: -0.0004

Data Index: 1020549 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0017. Min Act: -0.0004

Data Index: 1243147 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0017. Min Act: -0.0004

Data Index: 583129 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0016. Min Act: -0.0004

Data Index: 1235278 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0017. Min Act: -0.0004

Data Index: 1450218 (Python Code)

Max Activating Token Index: 7

Text #16

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0016. Min Act: -0.0004

Data Index: 944594 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0014. Min Act: -0.0004

Data Index: 1266927 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0016. Min Act: -0.0004

Data Index: 54386 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0016. Min Act: -0.0004

Data Index: 378449 (C4 (Web Text))

Max Activating Token Index: 26