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

Dataset: The Pile

Neuron 4777 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.5210. Min Act: -0.0000

Data Index: 421208 (The Pile)

Max Activating Token Index: 1006

Text #1

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.2010. Min Act: -0.0000

Data Index: 461454 (The Pile)

Max Activating Token Index: 520

Text #2

Max Range: 1.5210. Min Range: -1.5210

Max Act: 0.9363. Min Act: -0.0000

Data Index: 1241296 (The Pile)

Max Activating Token Index: 273

Text #3

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.2591. Min Act: -0.0000

Data Index: 1914015 (The Pile)

Max Activating Token Index: 273

Text #4

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.0977. Min Act: -0.0000

Data Index: 1282281 (The Pile)

Max Activating Token Index: 120

Text #5

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.1451. Min Act: 0.0000

Data Index: 1470320 (The Pile)

Max Activating Token Index: 352

Text #6

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.1188. Min Act: -0.0000

Data Index: 1589048 (The Pile)

Max Activating Token Index: 435

Text #7

Max Range: 1.5210. Min Range: -1.5210

Max Act: 0.9870. Min Act: -0.0000

Data Index: 421678 (The Pile)

Max Activating Token Index: 963

Text #8

Max Range: 1.5210. Min Range: -1.5210

Max Act: 0.9847. Min Act: -0.0000

Data Index: 173748 (The Pile)

Max Activating Token Index: 977

Text #9

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.0058. Min Act: -0.0000

Data Index: 1271874 (The Pile)

Max Activating Token Index: 68

Text #10

Max Range: 1.5210. Min Range: -1.5210

Max Act: 0.9883. Min Act: -0.0000

Data Index: 1875685 (The Pile)

Max Activating Token Index: 836

Text #11

Max Range: 1.5210. Min Range: -1.5210

Max Act: 0.8813. Min Act: -0.0000

Data Index: 1151607 (The Pile)

Max Activating Token Index: 962

Text #12

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.0246. Min Act: -0.0000

Data Index: 397956 (The Pile)

Max Activating Token Index: 721

Text #13

Max Range: 1.5210. Min Range: -1.5210

Max Act: 0.9559. Min Act: -0.0000

Data Index: 1851015 (The Pile)

Max Activating Token Index: 11

Text #14

Max Range: 1.5210. Min Range: -1.5210

Max Act: 0.9149. Min Act: -0.0000

Data Index: 4388 (The Pile)

Max Activating Token Index: 55

Text #15

Max Range: 1.5210. Min Range: -1.5210

Max Act: 0.8789. Min Act: -0.0000

Data Index: 401642 (The Pile)

Max Activating Token Index: 341

Text #16

Max Range: 1.5210. Min Range: -1.5210

Max Act: 0.9515. Min Act: -0.0000

Data Index: 167172 (The Pile)

Max Activating Token Index: 283

Text #17

Max Range: 1.5210. Min Range: -1.5210

Max Act: 0.8700. Min Act: 0.0000

Data Index: 768312 (The Pile)

Max Activating Token Index: 702

Text #18

Max Range: 1.5210. Min Range: -1.5210

Max Act: 0.9876. Min Act: -0.0000

Data Index: 47105 (The Pile)

Max Activating Token Index: 280

Text #19

Max Range: 1.5210. Min Range: -1.5210

Max Act: 0.8887. Min Act: -0.0000

Data Index: 1473507 (The Pile)

Max Activating Token Index: 629