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

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

Neuron 3642 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5889. Min Range: -2.5889

Max Act: 2.4683. Min Act: 0.0004

Data Index: 1561405 (Python Code)

Max Activating Token Index: 225

Text #1

Max Range: 2.5889. Min Range: -2.5889

Max Act: 2.5889. Min Act: 0.0003

Data Index: 1468880 (Python Code)

Max Activating Token Index: 808

Text #2

Max Range: 2.5889. Min Range: -2.5889

Max Act: 2.2205. Min Act: -0.0000

Data Index: 1470308 (Python Code)

Max Activating Token Index: 803

Text #3

Max Range: 2.5889. Min Range: -2.5889

Max Act: 2.4410. Min Act: 0.0002

Data Index: 1429962 (Python Code)

Max Activating Token Index: 86

Text #4

Max Range: 2.5889. Min Range: -2.5889

Max Act: 2.4415. Min Act: -0.0000

Data Index: 1494975 (Python Code)

Max Activating Token Index: 472

Text #5

Max Range: 2.5889. Min Range: -2.5889

Max Act: 2.3818. Min Act: -0.0000

Data Index: 1477521 (Python Code)

Max Activating Token Index: 123

Text #6

Max Range: 2.5889. Min Range: -2.5889

Max Act: 2.1564. Min Act: -0.0000

Data Index: 1639972 (Python Code)

Max Activating Token Index: 677

Text #7

Max Range: 2.5889. Min Range: -2.5889

Max Act: 2.1775. Min Act: -0.0000

Data Index: 1507950 (Python Code)

Max Activating Token Index: 311

Text #8

Max Range: 2.5889. Min Range: -2.5889

Max Act: 2.2353. Min Act: -0.0000

Data Index: 1495289 (Python Code)

Max Activating Token Index: 22

Text #9

Max Range: 2.5889. Min Range: -2.5889

Max Act: 1.9729. Min Act: -0.0000

Data Index: 1554162 (Python Code)

Max Activating Token Index: 736

Text #10

Max Range: 2.5889. Min Range: -2.5889

Max Act: 2.0299. Min Act: -0.0000

Data Index: 1629297 (Python Code)

Max Activating Token Index: 105

Text #11

Max Range: 2.5889. Min Range: -2.5889

Max Act: 1.8945. Min Act: 0.0001

Data Index: 1562020 (Python Code)

Max Activating Token Index: 367

Text #12

Max Range: 2.5889. Min Range: -2.5889

Max Act: 2.1261. Min Act: 0.0000

Data Index: 1508590 (Python Code)

Max Activating Token Index: 73

Text #13

Max Range: 2.5889. Min Range: -2.5889

Max Act: 1.8973. Min Act: -0.0000

Data Index: 1419243 (Python Code)

Max Activating Token Index: 538

Text #14

Max Range: 2.5889. Min Range: -2.5889

Max Act: 1.9813. Min Act: 0.0002

Data Index: 1619889 (Python Code)

Max Activating Token Index: 56

Text #15

Max Range: 2.5889. Min Range: -2.5889

Max Act: 1.8806. Min Act: -0.0000

Data Index: 1414030 (Python Code)

Max Activating Token Index: 169

Text #16

Max Range: 2.5889. Min Range: -2.5889

Max Act: 1.9794. Min Act: -0.0000

Data Index: 1647598 (Python Code)

Max Activating Token Index: 626

Text #17

Max Range: 2.5889. Min Range: -2.5889

Max Act: 1.9725. Min Act: 0.0005

Data Index: 1447162 (Python Code)

Max Activating Token Index: 870

Text #18

Max Range: 2.5889. Min Range: -2.5889

Max Act: 1.9769. Min Act: -0.0000

Data Index: 1650308 (Python Code)

Max Activating Token Index: 354

Text #19

Max Range: 2.5889. Min Range: -2.5889

Max Act: 1.9435. Min Act: 0.0000

Data Index: 1469097 (Python Code)

Max Activating Token Index: 121