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

Dataset: The Pile

Neuron 1794 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.3809. Min Act: -0.0000

Data Index: 230178 (The Pile)

Max Activating Token Index: 356

Text #1

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.3666. Min Act: -0.0000

Data Index: 1877340 (The Pile)

Max Activating Token Index: 817

Text #2

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.3440. Min Act: -0.0000

Data Index: 885374 (The Pile)

Max Activating Token Index: 41

Text #3

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.3400. Min Act: -0.0000

Data Index: 647004 (The Pile)

Max Activating Token Index: 398

Text #4

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.3211. Min Act: -0.0000

Data Index: 1248382 (The Pile)

Max Activating Token Index: 342

Text #5

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.3121. Min Act: -0.0000

Data Index: 1757021 (The Pile)

Max Activating Token Index: 321

Text #6

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.3125. Min Act: -0.0000

Data Index: 595109 (The Pile)

Max Activating Token Index: 668

Text #7

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2913. Min Act: -0.0000

Data Index: 702478 (The Pile)

Max Activating Token Index: 343

Text #8

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2925. Min Act: -0.0000

Data Index: 300391 (The Pile)

Max Activating Token Index: 244

Text #9

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2735. Min Act: -0.0000

Data Index: 326358 (The Pile)

Max Activating Token Index: 723

Text #10

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2870. Min Act: -0.0000

Data Index: 1854870 (The Pile)

Max Activating Token Index: 678

Text #11

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2729. Min Act: -0.0000

Data Index: 11088 (The Pile)

Max Activating Token Index: 447

Text #12

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2681. Min Act: -0.0000

Data Index: 424277 (The Pile)

Max Activating Token Index: 486

Text #13

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2864. Min Act: -0.0000

Data Index: 1885522 (The Pile)

Max Activating Token Index: 691

Text #14

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2791. Min Act: -0.0000

Data Index: 91858 (The Pile)

Max Activating Token Index: 189

Text #15

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2593. Min Act: -0.0000

Data Index: 447013 (The Pile)

Max Activating Token Index: 163

Text #16

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2640. Min Act: -0.0000

Data Index: 696098 (The Pile)

Max Activating Token Index: 420

Text #17

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2530. Min Act: -0.0000

Data Index: 331779 (The Pile)

Max Activating Token Index: 683

Text #18

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2620. Min Act: -0.0000

Data Index: 210587 (The Pile)

Max Activating Token Index: 308

Text #19

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2581. Min Act: -0.0000

Data Index: 322896 (The Pile)

Max Activating Token Index: 34