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

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

Neuron 1862 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.7218. Min Act: -0.0000

Data Index: 1376954 (Python Code)

Max Activating Token Index: 24

Text #1

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.6658. Min Act: -0.0000

Data Index: 1450608 (Python Code)

Max Activating Token Index: 157

Text #2

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.6509. Min Act: -0.0000

Data Index: 1559779 (Python Code)

Max Activating Token Index: 25

Text #3

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.4722. Min Act: -0.0000

Data Index: 1614648 (Python Code)

Max Activating Token Index: 188

Text #4

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.5322. Min Act: -0.0000

Data Index: 1465387 (Python Code)

Max Activating Token Index: 27

Text #5

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.5322. Min Act: -0.0000

Data Index: 1655950 (Python Code)

Max Activating Token Index: 27

Text #6

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.4072. Min Act: -0.0000

Data Index: 1564270 (Python Code)

Max Activating Token Index: 115

Text #7

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.5715. Min Act: -0.0000

Data Index: 1521531 (Python Code)

Max Activating Token Index: 27

Text #8

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.5631. Min Act: -0.0000

Data Index: 1546272 (Python Code)

Max Activating Token Index: 38

Text #9

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.3635. Min Act: -0.0000

Data Index: 1649909 (Python Code)

Max Activating Token Index: 28

Text #10

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.3635. Min Act: -0.0000

Data Index: 1563363 (Python Code)

Max Activating Token Index: 28

Text #11

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.2667. Min Act: -0.0000

Data Index: 1624391 (Python Code)

Max Activating Token Index: 210

Text #12

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.4421. Min Act: -0.0000

Data Index: 1386796 (Python Code)

Max Activating Token Index: 55

Text #13

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.4161. Min Act: -0.0000

Data Index: 1559744 (Python Code)

Max Activating Token Index: 59

Text #14

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.4883. Min Act: -0.0000

Data Index: 1469972 (Python Code)

Max Activating Token Index: 55

Text #15

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.4806. Min Act: -0.0000

Data Index: 1413254 (Python Code)

Max Activating Token Index: 137

Text #16

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.3093. Min Act: -0.0000

Data Index: 1435528 (Python Code)

Max Activating Token Index: 39

Text #17

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.5060. Min Act: -0.0000

Data Index: 1413606 (Python Code)

Max Activating Token Index: 98

Text #18

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.4519. Min Act: -0.0000

Data Index: 1564449 (Python Code)

Max Activating Token Index: 255

Text #19

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.3923. Min Act: -0.0000

Data Index: 1501954 (Python Code)

Max Activating Token Index: 66