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

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

Neuron 3863 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4075. Min Range: -1.4075

Max Act: 1.3928. Min Act: -0.0001

Data Index: 763665 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 1.4075. Min Range: -1.4075

Max Act: 1.4075. Min Act: -0.0001

Data Index: 1205930 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 1.4075. Min Range: -1.4075

Max Act: 1.3143. Min Act: -0.0000

Data Index: 513528 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 1.4075. Min Range: -1.4075

Max Act: 1.2769. Min Act: -0.0000

Data Index: 464871 (C4 (Web Text))

Max Activating Token Index: 238

Text #4

Max Range: 1.4075. Min Range: -1.4075

Max Act: 1.3076. Min Act: -0.0001

Data Index: 445513 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 1.4075. Min Range: -1.4075

Max Act: 1.2551. Min Act: -0.0001

Data Index: 265241 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 1.4075. Min Range: -1.4075

Max Act: 1.2058. Min Act: -0.0001

Data Index: 598948 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 1.4075. Min Range: -1.4075

Max Act: 1.2716. Min Act: -0.0001

Data Index: 112503 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 1.4075. Min Range: -1.4075

Max Act: 1.2684. Min Act: -0.0000

Data Index: 653992 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 1.4075. Min Range: -1.4075

Max Act: 1.2487. Min Act: -0.0001

Data Index: 724101 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 1.4075. Min Range: -1.4075

Max Act: 1.2276. Min Act: -0.0001

Data Index: 326012 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 1.4075. Min Range: -1.4075

Max Act: 1.1590. Min Act: -0.0001

Data Index: 440271 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 1.4075. Min Range: -1.4075

Max Act: 1.2992. Min Act: -0.0001

Data Index: 919835 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 1.4075. Min Range: -1.4075

Max Act: 1.2056. Min Act: -0.0000

Data Index: 622304 (C4 (Web Text))

Max Activating Token Index: 653

Text #14

Max Range: 1.4075. Min Range: -1.4075

Max Act: 1.1234. Min Act: -0.0000

Data Index: 423028 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 1.4075. Min Range: -1.4075

Max Act: 1.2512. Min Act: -0.0001

Data Index: 1307507 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 1.4075. Min Range: -1.4075

Max Act: 1.1817. Min Act: -0.0001

Data Index: 292755 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 1.4075. Min Range: -1.4075

Max Act: 1.1789. Min Act: -0.0001

Data Index: 825062 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 1.4075. Min Range: -1.4075

Max Act: 1.0990. Min Act: -0.0001

Data Index: 738242 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 1.4075. Min Range: -1.4075

Max Act: 1.2346. Min Act: -0.0001

Data Index: 403830 (C4 (Web Text))

Max Activating Token Index: 599