Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1143 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0016. Min Act: -0.0001

Data Index: 472984 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0012. Min Act: -0.0001

Data Index: 482994 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0014. Min Act: -0.0001

Data Index: 785311 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0016. Min Act: -0.0001

Data Index: 757408 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0014. Min Act: -0.0001

Data Index: 216506 (C4 (Web Text))

Max Activating Token Index: 934

Text #5

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0011. Min Act: -0.0001

Data Index: 717460 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0011. Min Act: -0.0001

Data Index: 374472 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0007. Min Act: -0.0001

Data Index: 99764 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0008. Min Act: -0.0001

Data Index: 1288299 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0008. Min Act: -0.0001

Data Index: 577215 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0008. Min Act: -0.0001

Data Index: 1574313 (Python Code)

Max Activating Token Index: 744

Text #11

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0007. Min Act: -0.0001

Data Index: 1554668 (Python Code)

Max Activating Token Index: 297

Text #12

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0008. Min Act: -0.0001

Data Index: 1411022 (Python Code)

Max Activating Token Index: 421

Text #13

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0005. Min Act: -0.0001

Data Index: 978326 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0007. Min Act: -0.0001

Data Index: 1603536 (Python Code)

Max Activating Token Index: 627

Text #15

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0008. Min Act: -0.0001

Data Index: 1443471 (Python Code)

Max Activating Token Index: 452

Text #16

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0007. Min Act: -0.0001

Data Index: 850080 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0007. Min Act: -0.0001

Data Index: 102557 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0006. Min Act: -0.0001

Data Index: 282935 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0004. Min Act: -0.0001

Data Index: 1507460 (Python Code)

Max Activating Token Index: 829