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

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

Neuron 251 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1010. Min Act: -0.0001

Data Index: 1486956 (Python Code)

Max Activating Token Index: 215

Text #1

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1024. Min Act: -0.0001

Data Index: 1591875 (Python Code)

Max Activating Token Index: 557

Text #2

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1013. Min Act: -0.0001

Data Index: 467829 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0990. Min Act: -0.0001

Data Index: 1589678 (Python Code)

Max Activating Token Index: 821

Text #4

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0958. Min Act: -0.0001

Data Index: 694808 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1014. Min Act: -0.0001

Data Index: 1441885 (Python Code)

Max Activating Token Index: 145

Text #6

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0999. Min Act: -0.0001

Data Index: 1607108 (Python Code)

Max Activating Token Index: 120

Text #7

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0941. Min Act: -0.0001

Data Index: 150440 (C4 (Web Text))

Max Activating Token Index: 394

Text #8

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0974. Min Act: -0.0001

Data Index: 1615778 (Python Code)

Max Activating Token Index: 175

Text #9

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0954. Min Act: -0.0001

Data Index: 1414048 (Python Code)

Max Activating Token Index: 191

Text #10

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0940. Min Act: -0.0001

Data Index: 1447120 (Python Code)

Max Activating Token Index: 316

Text #11

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0961. Min Act: -0.0001

Data Index: 1517910 (Python Code)

Max Activating Token Index: 307

Text #12

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0950. Min Act: -0.0001

Data Index: 177249 (C4 (Web Text))

Max Activating Token Index: 519

Text #13

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0945. Min Act: -0.0001

Data Index: 121445 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0964. Min Act: -0.0001

Data Index: 1656111 (Python Code)

Max Activating Token Index: 897

Text #15

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0926. Min Act: -0.0000

Data Index: 287413 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0965. Min Act: -0.0001

Data Index: 1435701 (Python Code)

Max Activating Token Index: 356

Text #17

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0918. Min Act: -0.0001

Data Index: 1405364 (Python Code)

Max Activating Token Index: 28

Text #18

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0944. Min Act: -0.0001

Data Index: 1549849 (Python Code)

Max Activating Token Index: 222

Text #19

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0916. Min Act: -0.0001

Data Index: 1514708 (Python Code)

Max Activating Token Index: 871