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

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

Neuron 611 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.9805. Min Act: -0.0001

Data Index: 1416174 (Python Code)

Max Activating Token Index: 19

Text #1

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.9031. Min Act: -0.0001

Data Index: 1654420 (Python Code)

Max Activating Token Index: 297

Text #2

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.9303. Min Act: -0.0001

Data Index: 1620997 (Python Code)

Max Activating Token Index: 62

Text #3

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.8340. Min Act: -0.0001

Data Index: 1601110 (Python Code)

Max Activating Token Index: 60

Text #4

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.9082. Min Act: -0.0001

Data Index: 1485336 (Python Code)

Max Activating Token Index: 366

Text #5

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.8539. Min Act: -0.0001

Data Index: 1645420 (Python Code)

Max Activating Token Index: 356

Text #6

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.8448. Min Act: -0.0001

Data Index: 1553262 (Python Code)

Max Activating Token Index: 41

Text #7

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.8735. Min Act: -0.0001

Data Index: 1481050 (Python Code)

Max Activating Token Index: 40

Text #8

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.8471. Min Act: -0.0001

Data Index: 1650211 (Python Code)

Max Activating Token Index: 111

Text #9

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.8433. Min Act: -0.0001

Data Index: 1604465 (Python Code)

Max Activating Token Index: 829

Text #10

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.8386. Min Act: -0.0001

Data Index: 1468609 (Python Code)

Max Activating Token Index: 88

Text #11

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.8138. Min Act: -0.0001

Data Index: 1624077 (Python Code)

Max Activating Token Index: 29

Text #12

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.8112. Min Act: -0.0001

Data Index: 1569070 (Python Code)

Max Activating Token Index: 24

Text #13

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.8290. Min Act: -0.0001

Data Index: 1572986 (Python Code)

Max Activating Token Index: 183

Text #14

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.8032. Min Act: -0.0001

Data Index: 1487377 (Python Code)

Max Activating Token Index: 16

Text #15

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.8355. Min Act: -0.0001

Data Index: 1580091 (Python Code)

Max Activating Token Index: 122

Text #16

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7798. Min Act: -0.0001

Data Index: 1361382 (Python Code)

Max Activating Token Index: 34

Text #17

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7763. Min Act: -0.0001

Data Index: 1567994 (Python Code)

Max Activating Token Index: 39

Text #18

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.8014. Min Act: -0.0001

Data Index: 1624418 (Python Code)

Max Activating Token Index: 20

Text #19

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.8020. Min Act: -0.0001

Data Index: 1638588 (Python Code)

Max Activating Token Index: 487