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

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

Neuron 362 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: 2.6647. Min Range: -2.6647

Max Act: 2.6647. Min Act: -0.0000

Data Index: 511938 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 2.6647. Min Range: -2.6647

Max Act: 2.6528. Min Act: -0.0000

Data Index: 121783 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 2.6647. Min Range: -2.6647

Max Act: 2.5715. Min Act: -0.0000

Data Index: 373815 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 2.6647. Min Range: -2.6647

Max Act: 2.4071. Min Act: -0.0000

Data Index: 863086 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 2.6647. Min Range: -2.6647

Max Act: 2.3400. Min Act: -0.0000

Data Index: 301940 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 2.6647. Min Range: -2.6647

Max Act: 2.3354. Min Act: -0.0000

Data Index: 268744 (C4 (Web Text))

Max Activating Token Index: 196

Text #6

Max Range: 2.6647. Min Range: -2.6647

Max Act: 2.2139. Min Act: -0.0000

Data Index: 990743 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 2.6647. Min Range: -2.6647

Max Act: 2.3679. Min Act: -0.0000

Data Index: 273493 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 2.6647. Min Range: -2.6647

Max Act: 2.2281. Min Act: -0.0000

Data Index: 825831 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 2.6647. Min Range: -2.6647

Max Act: 2.3261. Min Act: -0.0000

Data Index: 539527 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 2.6647. Min Range: -2.6647

Max Act: 2.2103. Min Act: -0.0000

Data Index: 10432 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 2.6647. Min Range: -2.6647

Max Act: 2.0215. Min Act: -0.0000

Data Index: 90392 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 2.6647. Min Range: -2.6647

Max Act: 2.1798. Min Act: -0.0000

Data Index: 544970 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 2.6647. Min Range: -2.6647

Max Act: 2.0769. Min Act: -0.0000

Data Index: 495499 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 2.6647. Min Range: -2.6647

Max Act: 2.0609. Min Act: -0.0000

Data Index: 530881 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 2.6647. Min Range: -2.6647

Max Act: 2.0972. Min Act: -0.0000

Data Index: 738705 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 2.6647. Min Range: -2.6647

Max Act: 2.0240. Min Act: -0.0000

Data Index: 119873 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 2.6647. Min Range: -2.6647

Max Act: 1.9722. Min Act: -0.0000

Data Index: 96482 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 2.6647. Min Range: -2.6647

Max Act: 1.7795. Min Act: -0.0000

Data Index: 1169899 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 2.6647. Min Range: -2.6647

Max Act: 2.0379. Min Act: -0.0000

Data Index: 1254064 (C4 (Web Text))

Max Activating Token Index: 73