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

Dataset: The Pile

Neuron 2115 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.2901. Min Act: -0.0000

Data Index: 1529946 (The Pile)

Max Activating Token Index: 176

Text #1

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.2364. Min Act: -0.0000

Data Index: 1127359 (The Pile)

Max Activating Token Index: 338

Text #2

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.2806. Min Act: -0.0000

Data Index: 831025 (The Pile)

Max Activating Token Index: 653

Text #3

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.1996. Min Act: -0.0000

Data Index: 6131 (The Pile)

Max Activating Token Index: 637

Text #4

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.2032. Min Act: -0.0000

Data Index: 804838 (The Pile)

Max Activating Token Index: 611

Text #5

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.2133. Min Act: -0.0000

Data Index: 710244 (The Pile)

Max Activating Token Index: 812

Text #6

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.1863. Min Act: -0.0000

Data Index: 1380740 (The Pile)

Max Activating Token Index: 268

Text #7

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.2241. Min Act: -0.0000

Data Index: 529082 (The Pile)

Max Activating Token Index: 231

Text #8

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.1791. Min Act: -0.0000

Data Index: 1636938 (The Pile)

Max Activating Token Index: 120

Text #9

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.1830. Min Act: -0.0000

Data Index: 885479 (The Pile)

Max Activating Token Index: 413

Text #10

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.1724. Min Act: -0.0000

Data Index: 799674 (The Pile)

Max Activating Token Index: 611

Text #11

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.1723. Min Act: -0.0000

Data Index: 510912 (The Pile)

Max Activating Token Index: 847

Text #12

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.1758. Min Act: -0.0000

Data Index: 1988919 (The Pile)

Max Activating Token Index: 142

Text #13

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.1696. Min Act: -0.0000

Data Index: 1314225 (The Pile)

Max Activating Token Index: 280

Text #14

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.1808. Min Act: -0.0000

Data Index: 540015 (The Pile)

Max Activating Token Index: 381

Text #15

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.1654. Min Act: -0.0000

Data Index: 1295149 (The Pile)

Max Activating Token Index: 340

Text #16

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.1704. Min Act: -0.0000

Data Index: 814918 (The Pile)

Max Activating Token Index: 603

Text #17

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.1737. Min Act: -0.0000

Data Index: 601196 (The Pile)

Max Activating Token Index: 727

Text #18

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.1632. Min Act: -0.0000

Data Index: 1672771 (The Pile)

Max Activating Token Index: 717

Text #19

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.1667. Min Act: -0.0000

Data Index: 281393 (The Pile)

Max Activating Token Index: 89