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

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

Neuron 2591 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.1014. Min Act: -0.0001

Data Index: 1376667 (Python Code)

Max Activating Token Index: 836

Text #1

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0986. Min Act: -0.0001

Data Index: 1391341 (Python Code)

Max Activating Token Index: 927

Text #2

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0906. Min Act: -0.0001

Data Index: 1590370 (Python Code)

Max Activating Token Index: 826

Text #3

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0806. Min Act: -0.0001

Data Index: 795340 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0810. Min Act: -0.0001

Data Index: 1018612 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0857. Min Act: -0.0001

Data Index: 1511492 (Python Code)

Max Activating Token Index: 755

Text #6

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0826. Min Act: -0.0001

Data Index: 1408545 (Python Code)

Max Activating Token Index: 582

Text #7

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0799. Min Act: -0.0001

Data Index: 402567 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0846. Min Act: -0.0001

Data Index: 1378177 (Python Code)

Max Activating Token Index: 952

Text #9

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0847. Min Act: -0.0001

Data Index: 1396209 (Python Code)

Max Activating Token Index: 695

Text #10

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0796. Min Act: -0.0001

Data Index: 1412845 (Python Code)

Max Activating Token Index: 744

Text #11

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0846. Min Act: -0.0001

Data Index: 1570610 (Python Code)

Max Activating Token Index: 960

Text #12

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0783. Min Act: -0.0001

Data Index: 1645598 (Python Code)

Max Activating Token Index: 711

Text #13

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0813. Min Act: -0.0001

Data Index: 1612446 (Python Code)

Max Activating Token Index: 834

Text #14

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0782. Min Act: -0.0001

Data Index: 1481790 (Python Code)

Max Activating Token Index: 720

Text #15

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0802. Min Act: -0.0001

Data Index: 1195823 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0765. Min Act: -0.0001

Data Index: 1401580 (Python Code)

Max Activating Token Index: 464

Text #17

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0763. Min Act: -0.0001

Data Index: 395238 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0796. Min Act: -0.0001

Data Index: 1482468 (Python Code)

Max Activating Token Index: 885

Text #19

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0764. Min Act: -0.0001

Data Index: 1102945 (C4 (Web Text))

Max Activating Token Index: 159