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

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

Neuron 3240 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9910. Min Range: -1.9910

Max Act: 1.9910. Min Act: -0.0000

Data Index: 759787 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 1.9910. Min Range: -1.9910

Max Act: 1.5046. Min Act: -0.0000

Data Index: 890671 (C4 (Web Text))

Max Activating Token Index: 489

Text #2

Max Range: 1.9910. Min Range: -1.9910

Max Act: 1.4549. Min Act: -0.0000

Data Index: 399527 (C4 (Web Text))

Max Activating Token Index: 511

Text #3

Max Range: 1.9910. Min Range: -1.9910

Max Act: 1.4533. Min Act: -0.0000

Data Index: 813447 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 1.9910. Min Range: -1.9910

Max Act: 1.4524. Min Act: -0.0000

Data Index: 776938 (C4 (Web Text))

Max Activating Token Index: 413

Text #5

Max Range: 1.9910. Min Range: -1.9910

Max Act: 1.3190. Min Act: -0.0000

Data Index: 1008223 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 1.9910. Min Range: -1.9910

Max Act: 1.3532. Min Act: -0.0000

Data Index: 687440 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 1.9910. Min Range: -1.9910

Max Act: 1.3108. Min Act: -0.0000

Data Index: 1118853 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 1.9910. Min Range: -1.9910

Max Act: 1.3721. Min Act: -0.0000

Data Index: 920473 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 1.9910. Min Range: -1.9910

Max Act: 1.3936. Min Act: -0.0000

Data Index: 755830 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 1.9910. Min Range: -1.9910

Max Act: 1.2257. Min Act: -0.0000

Data Index: 379413 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 1.9910. Min Range: -1.9910

Max Act: 1.2981. Min Act: -0.0000

Data Index: 343957 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 1.9910. Min Range: -1.9910

Max Act: 1.2474. Min Act: -0.0000

Data Index: 1193874 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 1.9910. Min Range: -1.9910

Max Act: 1.1736. Min Act: -0.0000

Data Index: 344298 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 1.9910. Min Range: -1.9910

Max Act: 1.1828. Min Act: -0.0000

Data Index: 156832 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 1.9910. Min Range: -1.9910

Max Act: 1.2410. Min Act: -0.0000

Data Index: 92924 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 1.9910. Min Range: -1.9910

Max Act: 1.1928. Min Act: -0.0000

Data Index: 1112865 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 1.9910. Min Range: -1.9910

Max Act: 1.2076. Min Act: -0.0000

Data Index: 782979 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 1.9910. Min Range: -1.9910

Max Act: 1.1604. Min Act: -0.0000

Data Index: 863261 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 1.9910. Min Range: -1.9910

Max Act: 1.1880. Min Act: -0.0000

Data Index: 21010 (C4 (Web Text))

Max Activating Token Index: 393