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

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

Neuron 1707 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0604. Min Range: -2.0604

Max Act: 2.0133. Min Act: -0.0000

Data Index: 1451766 (Python Code)

Max Activating Token Index: 85

Text #1

Max Range: 2.0604. Min Range: -2.0604

Max Act: 2.0604. Min Act: -0.0000

Data Index: 1604295 (Python Code)

Max Activating Token Index: 29

Text #2

Max Range: 2.0604. Min Range: -2.0604

Max Act: 1.8934. Min Act: -0.0000

Data Index: 1388300 (Python Code)

Max Activating Token Index: 17

Text #3

Max Range: 2.0604. Min Range: -2.0604

Max Act: 1.8217. Min Act: -0.0000

Data Index: 1576014 (Python Code)

Max Activating Token Index: 89

Text #4

Max Range: 2.0604. Min Range: -2.0604

Max Act: 1.7146. Min Act: -0.0000

Data Index: 1466115 (Python Code)

Max Activating Token Index: 34

Text #5

Max Range: 2.0604. Min Range: -2.0604

Max Act: 1.7073. Min Act: -0.0000

Data Index: 1571882 (Python Code)

Max Activating Token Index: 43

Text #6

Max Range: 2.0604. Min Range: -2.0604

Max Act: 1.8638. Min Act: -0.0000

Data Index: 1420887 (Python Code)

Max Activating Token Index: 68

Text #7

Max Range: 2.0604. Min Range: -2.0604

Max Act: 1.7094. Min Act: -0.0000

Data Index: 1585954 (Python Code)

Max Activating Token Index: 20

Text #8

Max Range: 2.0604. Min Range: -2.0604

Max Act: 1.7105. Min Act: -0.0000

Data Index: 1469401 (Python Code)

Max Activating Token Index: 24

Text #9

Max Range: 2.0604. Min Range: -2.0604

Max Act: 1.6400. Min Act: -0.0000

Data Index: 1481785 (Python Code)

Max Activating Token Index: 84

Text #10

Max Range: 2.0604. Min Range: -2.0604

Max Act: 1.5280. Min Act: -0.0000

Data Index: 1559213 (Python Code)

Max Activating Token Index: 289

Text #11

Max Range: 2.0604. Min Range: -2.0604

Max Act: 1.6431. Min Act: -0.0000

Data Index: 1453707 (Python Code)

Max Activating Token Index: 34

Text #12

Max Range: 2.0604. Min Range: -2.0604

Max Act: 1.6170. Min Act: -0.0000

Data Index: 1516856 (Python Code)

Max Activating Token Index: 21

Text #13

Max Range: 2.0604. Min Range: -2.0604

Max Act: 1.5923. Min Act: -0.0000

Data Index: 1610119 (Python Code)

Max Activating Token Index: 66

Text #14

Max Range: 2.0604. Min Range: -2.0604

Max Act: 1.6722. Min Act: -0.0000

Data Index: 1499083 (Python Code)

Max Activating Token Index: 386

Text #15

Max Range: 2.0604. Min Range: -2.0604

Max Act: 1.4986. Min Act: -0.0000

Data Index: 1523717 (Python Code)

Max Activating Token Index: 541

Text #16

Max Range: 2.0604. Min Range: -2.0604

Max Act: 1.4636. Min Act: -0.0000

Data Index: 1497165 (Python Code)

Max Activating Token Index: 132

Text #17

Max Range: 2.0604. Min Range: -2.0604

Max Act: 1.4902. Min Act: -0.0000

Data Index: 1440249 (Python Code)

Max Activating Token Index: 9

Text #18

Max Range: 2.0604. Min Range: -2.0604

Max Act: 1.5693. Min Act: -0.0000

Data Index: 237605 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 2.0604. Min Range: -2.0604

Max Act: 1.4996. Min Act: -0.0000

Data Index: 1585550 (Python Code)

Max Activating Token Index: 216