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

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

Neuron 3979 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0732. Min Range: -5.0732

Max Act: 4.9209. Min Act: -0.0000

Data Index: 932778 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 5.0732. Min Range: -5.0732

Max Act: 5.0732. Min Act: -0.0000

Data Index: 746335 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 5.0732. Min Range: -5.0732

Max Act: 4.8303. Min Act: -0.0000

Data Index: 782881 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 5.0732. Min Range: -5.0732

Max Act: 4.5513. Min Act: -0.0000

Data Index: 747349 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 5.0732. Min Range: -5.0732

Max Act: 4.2878. Min Act: -0.0000

Data Index: 274681 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 5.0732. Min Range: -5.0732

Max Act: 4.0671. Min Act: -0.0000

Data Index: 753925 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 5.0732. Min Range: -5.0732

Max Act: 4.2288. Min Act: -0.0000

Data Index: 1210661 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 5.0732. Min Range: -5.0732

Max Act: 3.9488. Min Act: -0.0000

Data Index: 24013 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 5.0732. Min Range: -5.0732

Max Act: 3.9643. Min Act: -0.0000

Data Index: 819497 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 5.0732. Min Range: -5.0732

Max Act: 4.0786. Min Act: -0.0000

Data Index: 1043839 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 5.0732. Min Range: -5.0732

Max Act: 3.8781. Min Act: -0.0000

Data Index: 251478 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 5.0732. Min Range: -5.0732

Max Act: 3.8925. Min Act: -0.0000

Data Index: 883817 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 5.0732. Min Range: -5.0732

Max Act: 3.6452. Min Act: -0.0000

Data Index: 37947 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 5.0732. Min Range: -5.0732

Max Act: 3.8828. Min Act: -0.0000

Data Index: 732332 (C4 (Web Text))

Max Activating Token Index: 560

Text #14

Max Range: 5.0732. Min Range: -5.0732

Max Act: 3.7030. Min Act: -0.0000

Data Index: 1299219 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 5.0732. Min Range: -5.0732

Max Act: 3.6838. Min Act: -0.0000

Data Index: 1158744 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 5.0732. Min Range: -5.0732

Max Act: 3.6338. Min Act: -0.0000

Data Index: 560810 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 5.0732. Min Range: -5.0732

Max Act: 3.5859. Min Act: -0.0000

Data Index: 386837 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 5.0732. Min Range: -5.0732

Max Act: 3.3927. Min Act: -0.0000

Data Index: 376311 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 5.0732. Min Range: -5.0732

Max Act: 3.3734. Min Act: -0.0000

Data Index: 810175 (C4 (Web Text))

Max Activating Token Index: 224