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

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

Neuron 1578 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4556. Min Range: -2.4556

Max Act: 2.4556. Min Act: -0.0000

Data Index: 1647076 (Python Code)

Max Activating Token Index: 232

Text #1

Max Range: 2.4556. Min Range: -2.4556

Max Act: 2.3388. Min Act: 0.0000

Data Index: 1378011 (Python Code)

Max Activating Token Index: 155

Text #2

Max Range: 2.4556. Min Range: -2.4556

Max Act: 2.2053. Min Act: -0.0000

Data Index: 1504231 (Python Code)

Max Activating Token Index: 525

Text #3

Max Range: 2.4556. Min Range: -2.4556

Max Act: 2.1056. Min Act: 0.0001

Data Index: 1391285 (Python Code)

Max Activating Token Index: 415

Text #4

Max Range: 2.4556. Min Range: -2.4556

Max Act: 2.3035. Min Act: -0.0000

Data Index: 1609478 (Python Code)

Max Activating Token Index: 945

Text #5

Max Range: 2.4556. Min Range: -2.4556

Max Act: 2.1908. Min Act: 0.0001

Data Index: 1616131 (Python Code)

Max Activating Token Index: 253

Text #6

Max Range: 2.4556. Min Range: -2.4556

Max Act: 2.1443. Min Act: 0.0000

Data Index: 1443058 (Python Code)

Max Activating Token Index: 642

Text #7

Max Range: 2.4556. Min Range: -2.4556

Max Act: 2.2685. Min Act: -0.0000

Data Index: 1461966 (Python Code)

Max Activating Token Index: 494

Text #8

Max Range: 2.4556. Min Range: -2.4556

Max Act: 2.1773. Min Act: -0.0000

Data Index: 1593590 (Python Code)

Max Activating Token Index: 1010

Text #9

Max Range: 2.4556. Min Range: -2.4556

Max Act: 2.1449. Min Act: -0.0000

Data Index: 1652669 (Python Code)

Max Activating Token Index: 654

Text #10

Max Range: 2.4556. Min Range: -2.4556

Max Act: 2.1865. Min Act: 0.0000

Data Index: 1564594 (Python Code)

Max Activating Token Index: 31

Text #11

Max Range: 2.4556. Min Range: -2.4556

Max Act: 2.0971. Min Act: 0.0001

Data Index: 1611749 (Python Code)

Max Activating Token Index: 433

Text #12

Max Range: 2.4556. Min Range: -2.4556

Max Act: 2.2138. Min Act: 0.0000

Data Index: 1373903 (Python Code)

Max Activating Token Index: 244

Text #13

Max Range: 2.4556. Min Range: -2.4556

Max Act: 2.0997. Min Act: -0.0000

Data Index: 1489212 (Python Code)

Max Activating Token Index: 22

Text #14

Max Range: 2.4556. Min Range: -2.4556

Max Act: 1.9824. Min Act: -0.0000

Data Index: 1652891 (Python Code)

Max Activating Token Index: 989

Text #15

Max Range: 2.4556. Min Range: -2.4556

Max Act: 2.0887. Min Act: 0.0002

Data Index: 1557774 (Python Code)

Max Activating Token Index: 313

Text #16

Max Range: 2.4556. Min Range: -2.4556

Max Act: 2.1041. Min Act: -0.0000

Data Index: 1457913 (Python Code)

Max Activating Token Index: 604

Text #17

Max Range: 2.4556. Min Range: -2.4556

Max Act: 1.9687. Min Act: -0.0000

Data Index: 1623162 (Python Code)

Max Activating Token Index: 983

Text #18

Max Range: 2.4556. Min Range: -2.4556

Max Act: 2.0738. Min Act: -0.0000

Data Index: 1578312 (Python Code)

Max Activating Token Index: 779

Text #19

Max Range: 2.4556. Min Range: -2.4556

Max Act: 2.1153. Min Act: -0.0000

Data Index: 1420149 (Python Code)

Max Activating Token Index: 857