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

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

Neuron 324 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 15.7294. Min Range: -15.7294

Max Act: 15.7294. Min Act: -0.0001

Data Index: 132387 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 15.7294. Min Range: -15.7294

Max Act: 15.7205. Min Act: -0.0001

Data Index: 1604322 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 15.7294. Min Range: -15.7294

Max Act: 12.3840. Min Act: -0.0001

Data Index: 1455364 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 15.7294. Min Range: -15.7294

Max Act: 11.5949. Min Act: -0.0001

Data Index: 1387545 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 15.7294. Min Range: -15.7294

Max Act: 11.5266. Min Act: -0.0001

Data Index: 1435073 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 15.7294. Min Range: -15.7294

Max Act: 9.0991. Min Act: -0.0001

Data Index: 936847 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 15.7294. Min Range: -15.7294

Max Act: 10.9786. Min Act: -0.0001

Data Index: 1395431 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 15.7294. Min Range: -15.7294

Max Act: 9.9186. Min Act: -0.0001

Data Index: 1588080 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 15.7294. Min Range: -15.7294

Max Act: 11.1556. Min Act: -0.0001

Data Index: 1651347 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 15.7294. Min Range: -15.7294

Max Act: 11.0729. Min Act: -0.0001

Data Index: 1468947 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 15.7294. Min Range: -15.7294

Max Act: 10.8955. Min Act: -0.0001

Data Index: 1588288 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 15.7294. Min Range: -15.7294

Max Act: 10.7900. Min Act: -0.0001

Data Index: 1608884 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 15.7294. Min Range: -15.7294

Max Act: 10.7808. Min Act: -0.0001

Data Index: 1549941 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 15.7294. Min Range: -15.7294

Max Act: 10.6983. Min Act: -0.0001

Data Index: 1439514 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 15.7294. Min Range: -15.7294

Max Act: 10.5299. Min Act: -0.0001

Data Index: 1399752 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 15.7294. Min Range: -15.7294

Max Act: 10.5285. Min Act: -0.0001

Data Index: 1525471 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 15.7294. Min Range: -15.7294

Max Act: 10.5556. Min Act: -0.0001

Data Index: 1639703 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 15.7294. Min Range: -15.7294

Max Act: 9.7459. Min Act: -0.0001

Data Index: 1598719 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 15.7294. Min Range: -15.7294

Max Act: 8.4784. Min Act: -0.0001

Data Index: 1228931 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 15.7294. Min Range: -15.7294

Max Act: 9.8385. Min Act: -0.0001

Data Index: 567372 (C4 (Web Text))

Max Activating Token Index: 1023