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

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

Neuron 3708 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.1080. Min Act: -0.0002

Data Index: 928434 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.1074. Min Act: -0.0002

Data Index: 1338227 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.1039. Min Act: -0.0002

Data Index: 453210 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.1056. Min Act: -0.0002

Data Index: 417670 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.1029. Min Act: -0.0002

Data Index: 251635 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.1008. Min Act: -0.0002

Data Index: 462158 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0953. Min Act: -0.0002

Data Index: 894822 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0906. Min Act: -0.0002

Data Index: 405617 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0971. Min Act: -0.0002

Data Index: 334463 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0945. Min Act: -0.0002

Data Index: 490622 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0916. Min Act: -0.0002

Data Index: 1161658 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0893. Min Act: -0.0002

Data Index: 1171569 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0896. Min Act: -0.0002

Data Index: 916622 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0897. Min Act: -0.0002

Data Index: 1090958 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0907. Min Act: -0.0002

Data Index: 332705 (C4 (Web Text))

Max Activating Token Index: 538

Text #15

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0824. Min Act: -0.0002

Data Index: 935319 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0856. Min Act: -0.0002

Data Index: 748127 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0839. Min Act: -0.0002

Data Index: 814039 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0860. Min Act: -0.0002

Data Index: 353296 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0829. Min Act: -0.0002

Data Index: 341852 (C4 (Web Text))

Max Activating Token Index: 87