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

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

Neuron 1811 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: 0.0009. Min Range: -0.0009

Max Act: 0.0009. Min Act: -0.0001

Data Index: 1050044 (C4 (Web Text))

Max Activating Token Index: 234

Text #1

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0009. Min Act: -0.0001

Data Index: 405806 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0009. Min Act: -0.0001

Data Index: 308837 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0006. Min Act: -0.0001

Data Index: 1433366 (Python Code)

Max Activating Token Index: 989

Text #4

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0008. Min Act: -0.0001

Data Index: 818649 (C4 (Web Text))

Max Activating Token Index: 722

Text #5

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0007. Min Act: -0.0001

Data Index: 822690 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0006. Min Act: -0.0001

Data Index: 212922 (C4 (Web Text))

Max Activating Token Index: 703

Text #7

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0006. Min Act: -0.0001

Data Index: 26248 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0007. Min Act: -0.0001

Data Index: 35461 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0005. Min Act: -0.0001

Data Index: 520176 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0003. Min Act: -0.0001

Data Index: 972928 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0005. Min Act: -0.0001

Data Index: 155466 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0005. Min Act: -0.0001

Data Index: 536292 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0005. Min Act: -0.0002

Data Index: 600859 (C4 (Web Text))

Max Activating Token Index: 913

Text #14

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0005. Min Act: -0.0001

Data Index: 1014274 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0004. Min Act: -0.0001

Data Index: 1309342 (C4 (Web Text))

Max Activating Token Index: 224

Text #16

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0004. Min Act: -0.0001

Data Index: 663875 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0005. Min Act: -0.0001

Data Index: 1193324 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0005. Min Act: -0.0001

Data Index: 516854 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 0.0009. Min Range: -0.0009

Max Act: 0.0005. Min Act: -0.0001

Data Index: 976959 (C4 (Web Text))

Max Activating Token Index: 1019