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

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

Neuron 4883 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0341. Min Act: -0.0002

Data Index: 1125282 (C4 (Web Text))

Max Activating Token Index: 1

Text #1

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1370454 (Python Code)

Max Activating Token Index: 1

Text #2

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1466543 (Python Code)

Max Activating Token Index: 1

Text #3

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1541710 (Python Code)

Max Activating Token Index: 1

Text #4

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1458626 (Python Code)

Max Activating Token Index: 1

Text #5

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1538681 (Python Code)

Max Activating Token Index: 1

Text #6

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1536337 (Python Code)

Max Activating Token Index: 1

Text #7

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1414553 (Python Code)

Max Activating Token Index: 1

Text #8

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1529172 (Python Code)

Max Activating Token Index: 1

Text #9

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1524058 (Python Code)

Max Activating Token Index: 1

Text #10

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1454228 (Python Code)

Max Activating Token Index: 1

Text #11

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1460679 (Python Code)

Max Activating Token Index: 1

Text #12

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1443592 (Python Code)

Max Activating Token Index: 1

Text #13

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1365656 (Python Code)

Max Activating Token Index: 1

Text #14

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1513500 (Python Code)

Max Activating Token Index: 1

Text #15

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1506356 (Python Code)

Max Activating Token Index: 1

Text #16

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1486053 (Python Code)

Max Activating Token Index: 1

Text #17

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1397918 (Python Code)

Max Activating Token Index: 1

Text #18

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1484442 (Python Code)

Max Activating Token Index: 1

Text #19

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1475989 (Python Code)

Max Activating Token Index: 1