Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2527 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.5220. Min Act: -0.0000

Data Index: 184518 (The Pile)

Max Activating Token Index: 445

Text #1

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4614. Min Act: -0.0000

Data Index: 512174 (The Pile)

Max Activating Token Index: 732

Text #2

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4752. Min Act: -0.0000

Data Index: 1511831 (The Pile)

Max Activating Token Index: 669

Text #3

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4741. Min Act: -0.0000

Data Index: 1260813 (The Pile)

Max Activating Token Index: 128

Text #4

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4654. Min Act: -0.0000

Data Index: 194741 (The Pile)

Max Activating Token Index: 966

Text #5

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4322. Min Act: -0.0000

Data Index: 1468964 (The Pile)

Max Activating Token Index: 782

Text #6

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4301. Min Act: -0.0000

Data Index: 1377825 (The Pile)

Max Activating Token Index: 241

Text #7

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4417. Min Act: -0.0000

Data Index: 1554279 (The Pile)

Max Activating Token Index: 788

Text #8

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4275. Min Act: -0.0000

Data Index: 973559 (The Pile)

Max Activating Token Index: 477

Text #9

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4207. Min Act: -0.0000

Data Index: 796346 (The Pile)

Max Activating Token Index: 492

Text #10

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4296. Min Act: -0.0000

Data Index: 1254536 (The Pile)

Max Activating Token Index: 294

Text #11

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3958. Min Act: -0.0000

Data Index: 634999 (The Pile)

Max Activating Token Index: 283

Text #12

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3747. Min Act: -0.0000

Data Index: 1896342 (The Pile)

Max Activating Token Index: 711

Text #13

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4042. Min Act: -0.0000

Data Index: 159274 (The Pile)

Max Activating Token Index: 395

Text #14

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4091. Min Act: -0.0000

Data Index: 1419631 (The Pile)

Max Activating Token Index: 922

Text #15

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3866. Min Act: -0.0000

Data Index: 1683663 (The Pile)

Max Activating Token Index: 179

Text #16

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3855. Min Act: -0.0000

Data Index: 439898 (The Pile)

Max Activating Token Index: 911

Text #17

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3826. Min Act: -0.0000

Data Index: 1182921 (The Pile)

Max Activating Token Index: 121

Text #18

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3986. Min Act: -0.0000

Data Index: 1848964 (The Pile)

Max Activating Token Index: 55

Text #19

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3995. Min Act: -0.0000

Data Index: 947418 (The Pile)

Max Activating Token Index: 1020