Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3543 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.8930. Min Act: -0.0000

Data Index: 408546 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.9090. Min Act: -0.0000

Data Index: 758983 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.8741. Min Act: -0.0000

Data Index: 577645 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.7763. Min Act: -0.0000

Data Index: 780915 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.8460. Min Act: -0.0000

Data Index: 905525 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.8619. Min Act: -0.0000

Data Index: 437299 (C4 (Web Text))

Max Activating Token Index: 854

Text #6

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.7660. Min Act: -0.0000

Data Index: 610379 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.7375. Min Act: -0.0000

Data Index: 1238938 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.7138. Min Act: -0.0000

Data Index: 882461 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.7364. Min Act: -0.0000

Data Index: 1137650 (C4 (Web Text))

Max Activating Token Index: 394

Text #10

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.7794. Min Act: -0.0000

Data Index: 1156207 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.7249. Min Act: -0.0000

Data Index: 249686 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.7453. Min Act: -0.0000

Data Index: 127921 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.6953. Min Act: -0.0000

Data Index: 1252780 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.6913. Min Act: -0.0000

Data Index: 838175 (C4 (Web Text))

Max Activating Token Index: 413

Text #15

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.6986. Min Act: -0.0000

Data Index: 111353 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.6915. Min Act: -0.0000

Data Index: 156955 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.6804. Min Act: -0.0000

Data Index: 256766 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.6196. Min Act: -0.0000

Data Index: 109754 (C4 (Web Text))

Max Activating Token Index: 442

Text #19

Max Range: 0.9090. Min Range: -0.9090

Max Act: 0.6736. Min Act: -0.0000

Data Index: 258085 (C4 (Web Text))

Max Activating Token Index: 26