Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 616 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1397504 (Python Code)

Max Activating Token Index: 1

Text #1

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1429647 (Python Code)

Max Activating Token Index: 1

Text #2

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1427060 (Python Code)

Max Activating Token Index: 1

Text #3

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1419831 (Python Code)

Max Activating Token Index: 1

Text #4

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1365334 (Python Code)

Max Activating Token Index: 1

Text #5

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1377807 (Python Code)

Max Activating Token Index: 1

Text #6

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1418446 (Python Code)

Max Activating Token Index: 1

Text #7

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1389617 (Python Code)

Max Activating Token Index: 1

Text #8

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1389456 (Python Code)

Max Activating Token Index: 1

Text #9

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1386099 (Python Code)

Max Activating Token Index: 1

Text #10

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1385692 (Python Code)

Max Activating Token Index: 1

Text #11

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1418368 (Python Code)

Max Activating Token Index: 1

Text #12

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1408843 (Python Code)

Max Activating Token Index: 1

Text #13

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1394730 (Python Code)

Max Activating Token Index: 1

Text #14

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1385098 (Python Code)

Max Activating Token Index: 1

Text #15

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1401591 (Python Code)

Max Activating Token Index: 1

Text #16

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1404270 (Python Code)

Max Activating Token Index: 1

Text #17

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1416339 (Python Code)

Max Activating Token Index: 1

Text #18

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1371018 (Python Code)

Max Activating Token Index: 1

Text #19

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1401805 (Python Code)

Max Activating Token Index: 1