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

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

Neuron 5013 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: 0.1190. Min Range: -0.1190

Max Act: 0.1190. Min Act: -0.0002

Data Index: 1458283 (Python Code)

Max Activating Token Index: 997

Text #1

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.1137. Min Act: -0.0002

Data Index: 1394709 (Python Code)

Max Activating Token Index: 958

Text #2

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0990. Min Act: -0.0002

Data Index: 1504454 (Python Code)

Max Activating Token Index: 948

Text #3

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.1025. Min Act: -0.0002

Data Index: 1426336 (Python Code)

Max Activating Token Index: 460

Text #4

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.1024. Min Act: -0.0002

Data Index: 1575390 (Python Code)

Max Activating Token Index: 65

Text #5

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.1045. Min Act: -0.0002

Data Index: 1410199 (Python Code)

Max Activating Token Index: 48

Text #6

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0992. Min Act: -0.0002

Data Index: 1550652 (Python Code)

Max Activating Token Index: 1002

Text #7

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.1025. Min Act: -0.0002

Data Index: 1652047 (Python Code)

Max Activating Token Index: 609

Text #8

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0996. Min Act: -0.0002

Data Index: 1428384 (Python Code)

Max Activating Token Index: 843

Text #9

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0960. Min Act: -0.0002

Data Index: 1416369 (Python Code)

Max Activating Token Index: 984

Text #10

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0948. Min Act: -0.0002

Data Index: 1639870 (Python Code)

Max Activating Token Index: 927

Text #11

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0915. Min Act: -0.0002

Data Index: 1384813 (Python Code)

Max Activating Token Index: 816

Text #12

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0854. Min Act: -0.0002

Data Index: 1552982 (Python Code)

Max Activating Token Index: 892

Text #13

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0889. Min Act: -0.0002

Data Index: 1413807 (Python Code)

Max Activating Token Index: 978

Text #14

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0914. Min Act: -0.0002

Data Index: 1605511 (Python Code)

Max Activating Token Index: 105

Text #15

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0979. Min Act: -0.0002

Data Index: 1551519 (Python Code)

Max Activating Token Index: 860

Text #16

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0980. Min Act: -0.0002

Data Index: 1414514 (Python Code)

Max Activating Token Index: 30

Text #17

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0910. Min Act: -0.0002

Data Index: 1463666 (Python Code)

Max Activating Token Index: 782

Text #18

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0932. Min Act: -0.0002

Data Index: 1484925 (Python Code)

Max Activating Token Index: 267

Text #19

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0969. Min Act: -0.0002

Data Index: 1557685 (Python Code)

Max Activating Token Index: 560