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

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

Neuron 3616 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1516. Min Range: -2.1516

Max Act: 2.1516. Min Act: -0.0000

Data Index: 1580171 (Python Code)

Max Activating Token Index: 175

Text #1

Max Range: 2.1516. Min Range: -2.1516

Max Act: 2.0118. Min Act: -0.0000

Data Index: 1207637 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 2.1516. Min Range: -2.1516

Max Act: 1.7888. Min Act: -0.0000

Data Index: 754770 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 2.1516. Min Range: -2.1516

Max Act: 1.7113. Min Act: -0.0000

Data Index: 381148 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 2.1516. Min Range: -2.1516

Max Act: 1.5609. Min Act: -0.0000

Data Index: 760674 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 2.1516. Min Range: -2.1516

Max Act: 1.5498. Min Act: -0.0000

Data Index: 902139 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 2.1516. Min Range: -2.1516

Max Act: 1.5240. Min Act: -0.0000

Data Index: 306706 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 2.1516. Min Range: -2.1516

Max Act: 1.4333. Min Act: -0.0000

Data Index: 1020637 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 2.1516. Min Range: -2.1516

Max Act: 1.4212. Min Act: -0.0000

Data Index: 408907 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 2.1516. Min Range: -2.1516

Max Act: 1.4662. Min Act: -0.0000

Data Index: 646707 (C4 (Web Text))

Max Activating Token Index: 658

Text #10

Max Range: 2.1516. Min Range: -2.1516

Max Act: 1.4060. Min Act: -0.0000

Data Index: 785753 (C4 (Web Text))

Max Activating Token Index: 771

Text #11

Max Range: 2.1516. Min Range: -2.1516

Max Act: 1.3795. Min Act: -0.0000

Data Index: 1003036 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 2.1516. Min Range: -2.1516

Max Act: 1.4061. Min Act: -0.0000

Data Index: 1115760 (C4 (Web Text))

Max Activating Token Index: 293

Text #13

Max Range: 2.1516. Min Range: -2.1516

Max Act: 1.3985. Min Act: -0.0000

Data Index: 133699 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 2.1516. Min Range: -2.1516

Max Act: 1.4481. Min Act: -0.0000

Data Index: 1082698 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 2.1516. Min Range: -2.1516

Max Act: 1.3975. Min Act: -0.0000

Data Index: 43381 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 2.1516. Min Range: -2.1516

Max Act: 1.4134. Min Act: -0.0000

Data Index: 1396144 (Python Code)

Max Activating Token Index: 923

Text #17

Max Range: 2.1516. Min Range: -2.1516

Max Act: 1.3593. Min Act: -0.0000

Data Index: 1257807 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 2.1516. Min Range: -2.1516

Max Act: 1.3966. Min Act: -0.0000

Data Index: 285344 (C4 (Web Text))

Max Activating Token Index: 391

Text #19

Max Range: 2.1516. Min Range: -2.1516

Max Act: 1.3075. Min Act: -0.0000

Data Index: 1196845 (C4 (Web Text))

Max Activating Token Index: 453