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

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

Neuron 2135 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1703. Min Range: -2.1703

Max Act: 2.0895. Min Act: -0.0000

Data Index: 1085724 (C4 (Web Text))

Max Activating Token Index: 537

Text #1

Max Range: 2.1703. Min Range: -2.1703

Max Act: 2.1703. Min Act: -0.0000

Data Index: 460704 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 2.1703. Min Range: -2.1703

Max Act: 2.1366. Min Act: -0.0000

Data Index: 892233 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 2.1703. Min Range: -2.1703

Max Act: 2.0604. Min Act: -0.0000

Data Index: 979595 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 2.1703. Min Range: -2.1703

Max Act: 2.0574. Min Act: -0.0000

Data Index: 1078750 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 2.1703. Min Range: -2.1703

Max Act: 1.9399. Min Act: -0.0000

Data Index: 61391 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 2.1703. Min Range: -2.1703

Max Act: 2.0298. Min Act: -0.0000

Data Index: 142636 (C4 (Web Text))

Max Activating Token Index: 461

Text #7

Max Range: 2.1703. Min Range: -2.1703

Max Act: 2.1451. Min Act: -0.0000

Data Index: 1074883 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 2.1703. Min Range: -2.1703

Max Act: 1.9667. Min Act: -0.0000

Data Index: 524072 (C4 (Web Text))

Max Activating Token Index: 1005

Text #9

Max Range: 2.1703. Min Range: -2.1703

Max Act: 1.9267. Min Act: -0.0000

Data Index: 674430 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 2.1703. Min Range: -2.1703

Max Act: 1.9187. Min Act: -0.0000

Data Index: 51124 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 2.1703. Min Range: -2.1703

Max Act: 1.9061. Min Act: -0.0000

Data Index: 379594 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 2.1703. Min Range: -2.1703

Max Act: 1.8901. Min Act: -0.0000

Data Index: 1038001 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 2.1703. Min Range: -2.1703

Max Act: 1.7751. Min Act: -0.0000

Data Index: 161558 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 2.1703. Min Range: -2.1703

Max Act: 1.8289. Min Act: -0.0000

Data Index: 1043984 (C4 (Web Text))

Max Activating Token Index: 720

Text #15

Max Range: 2.1703. Min Range: -2.1703

Max Act: 1.8875. Min Act: -0.0000

Data Index: 94390 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 2.1703. Min Range: -2.1703

Max Act: 1.7781. Min Act: -0.0000

Data Index: 138518 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 2.1703. Min Range: -2.1703

Max Act: 1.7621. Min Act: -0.0000

Data Index: 331526 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 2.1703. Min Range: -2.1703

Max Act: 1.6571. Min Act: -0.0000

Data Index: 843843 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 2.1703. Min Range: -2.1703

Max Act: 1.7391. Min Act: -0.0000

Data Index: 948068 (C4 (Web Text))

Max Activating Token Index: 48