Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 484 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.1100. Min Act: -0.0003

Data Index: 1266378 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0937. Min Act: -0.0003

Data Index: 1190187 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0986. Min Act: -0.0003

Data Index: 560817 (C4 (Web Text))

Max Activating Token Index: 855

Text #3

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0975. Min Act: -0.0003

Data Index: 1259098 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.1004. Min Act: -0.0003

Data Index: 431440 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.1001. Min Act: -0.0003

Data Index: 1082653 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0880. Min Act: -0.0003

Data Index: 989946 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0902. Min Act: -0.0003

Data Index: 59474 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0892. Min Act: -0.0003

Data Index: 314477 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0892. Min Act: -0.0003

Data Index: 1032486 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0868. Min Act: -0.0003

Data Index: 497306 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0882. Min Act: -0.0003

Data Index: 192659 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0854. Min Act: -0.0003

Data Index: 676550 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0840. Min Act: -0.0003

Data Index: 1198770 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0876. Min Act: -0.0003

Data Index: 820184 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0820. Min Act: -0.0003

Data Index: 1209273 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0804. Min Act: -0.0003

Data Index: 32711 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0828. Min Act: -0.0003

Data Index: 865177 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0813. Min Act: -0.0003

Data Index: 538992 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0758. Min Act: -0.0003

Data Index: 495641 (C4 (Web Text))

Max Activating Token Index: 381