Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 115 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0902. Min Act: -0.0002

Data Index: 1016023 (C4 (Web Text))

Max Activating Token Index: 347

Text #1

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0850. Min Act: -0.0002

Data Index: 768283 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0844. Min Act: -0.0002

Data Index: 616028 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0771. Min Act: -0.0002

Data Index: 909840 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0725. Min Act: -0.0003

Data Index: 794921 (C4 (Web Text))

Max Activating Token Index: 110

Text #5

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0735. Min Act: -0.0002

Data Index: 1313042 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0756. Min Act: -0.0002

Data Index: 1045637 (C4 (Web Text))

Max Activating Token Index: 954

Text #7

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0696. Min Act: -0.0002

Data Index: 483097 (C4 (Web Text))

Max Activating Token Index: 884

Text #8

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0644. Min Act: -0.0002

Data Index: 483817 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0706. Min Act: -0.0002

Data Index: 46509 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0608. Min Act: -0.0002

Data Index: 339103 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0604. Min Act: -0.0002

Data Index: 464621 (C4 (Web Text))

Max Activating Token Index: 758

Text #12

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0610. Min Act: -0.0002

Data Index: 640381 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0641. Min Act: -0.0002

Data Index: 969216 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0579. Min Act: -0.0002

Data Index: 853812 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1331626 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0603. Min Act: -0.0002

Data Index: 756230 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0550. Min Act: -0.0002

Data Index: 1144449 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0556. Min Act: -0.0002

Data Index: 1349009 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0601. Min Act: -0.0002

Data Index: 668744 (C4 (Web Text))

Max Activating Token Index: 227