Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1491 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0016. Min Act: -0.0005

Data Index: 933543 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0016. Min Act: -0.0005

Data Index: 910411 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0015. Min Act: -0.0005

Data Index: 651054 (C4 (Web Text))

Max Activating Token Index: 952

Text #3

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0015. Min Act: -0.0005

Data Index: 1121033 (C4 (Web Text))

Max Activating Token Index: 979

Text #4

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0015. Min Act: -0.0005

Data Index: 1110660 (C4 (Web Text))

Max Activating Token Index: 1007

Text #5

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0015. Min Act: -0.0005

Data Index: 747893 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0015. Min Act: -0.0005

Data Index: 1352009 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0015. Min Act: -0.0005

Data Index: 97211 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0014. Min Act: -0.0005

Data Index: 1055288 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0015. Min Act: -0.0005

Data Index: 604661 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0014. Min Act: -0.0005

Data Index: 1129800 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0014. Min Act: -0.0005

Data Index: 802027 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0014. Min Act: -0.0005

Data Index: 765450 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0014. Min Act: -0.0005

Data Index: 897753 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0014. Min Act: -0.0005

Data Index: 479229 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0014. Min Act: -0.0004

Data Index: 866658 (C4 (Web Text))

Max Activating Token Index: 1

Text #16

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0014. Min Act: -0.0005

Data Index: 1341602 (C4 (Web Text))

Max Activating Token Index: 1017

Text #17

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0014. Min Act: -0.0005

Data Index: 882913 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0014. Min Act: -0.0005

Data Index: 1227461 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0014. Min Act: -0.0005

Data Index: 477885 (C4 (Web Text))

Max Activating Token Index: 993