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

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

Neuron 3686 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0013. Min Act: -0.0002

Data Index: 1637525 (Python Code)

Max Activating Token Index: 957

Text #1

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0012. Min Act: -0.0002

Data Index: 1382997 (Python Code)

Max Activating Token Index: 972

Text #2

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0010. Min Act: -0.0002

Data Index: 1615547 (Python Code)

Max Activating Token Index: 1017

Text #3

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0009. Min Act: -0.0002

Data Index: 1507842 (Python Code)

Max Activating Token Index: 1022

Text #4

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0009. Min Act: -0.0003

Data Index: 672485 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0008. Min Act: -0.0002

Data Index: 1517820 (Python Code)

Max Activating Token Index: 995

Text #6

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0008. Min Act: -0.0002

Data Index: 1376666 (Python Code)

Max Activating Token Index: 1017

Text #7

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0008. Min Act: -0.0002

Data Index: 1559803 (Python Code)

Max Activating Token Index: 1015

Text #8

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0009. Min Act: -0.0002

Data Index: 1385304 (Python Code)

Max Activating Token Index: 1005

Text #9

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0007. Min Act: -0.0002

Data Index: 598655 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0008. Min Act: -0.0002

Data Index: 1527616 (Python Code)

Max Activating Token Index: 985

Text #11

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0008. Min Act: -0.0002

Data Index: 1366445 (Python Code)

Max Activating Token Index: 971

Text #12

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0007. Min Act: -0.0002

Data Index: 1634412 (Python Code)

Max Activating Token Index: 1002

Text #13

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0008. Min Act: -0.0002

Data Index: 1421061 (Python Code)

Max Activating Token Index: 1004

Text #14

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0008. Min Act: -0.0003

Data Index: 519319 (C4 (Web Text))

Max Activating Token Index: 991

Text #15

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0008. Min Act: -0.0002

Data Index: 1254639 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0008. Min Act: -0.0003

Data Index: 510856 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0007. Min Act: -0.0003

Data Index: 1126058 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0007. Min Act: -0.0003

Data Index: 933888 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0007. Min Act: -0.0002

Data Index: 1634853 (Python Code)

Max Activating Token Index: 986