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

Dataset: The Pile

Neuron 1764 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2199. Min Range: -1.2199

Max Act: 1.2199. Min Act: -0.0000

Data Index: 490477 (The Pile)

Max Activating Token Index: 312

Text #1

Max Range: 1.2199. Min Range: -1.2199

Max Act: 0.8854. Min Act: -0.0000

Data Index: 1759944 (The Pile)

Max Activating Token Index: 188

Text #2

Max Range: 1.2199. Min Range: -1.2199

Max Act: 0.9657. Min Act: -0.0000

Data Index: 771990 (The Pile)

Max Activating Token Index: 132

Text #3

Max Range: 1.2199. Min Range: -1.2199

Max Act: 0.8892. Min Act: -0.0000

Data Index: 115581 (The Pile)

Max Activating Token Index: 547

Text #4

Max Range: 1.2199. Min Range: -1.2199

Max Act: 0.9069. Min Act: -0.0000

Data Index: 1604269 (The Pile)

Max Activating Token Index: 393

Text #5

Max Range: 1.2199. Min Range: -1.2199

Max Act: 0.8484. Min Act: -0.0000

Data Index: 999185 (The Pile)

Max Activating Token Index: 344

Text #6

Max Range: 1.2199. Min Range: -1.2199

Max Act: 0.8735. Min Act: -0.0000

Data Index: 1988001 (The Pile)

Max Activating Token Index: 424

Text #7

Max Range: 1.2199. Min Range: -1.2199

Max Act: 0.7403. Min Act: -0.0000

Data Index: 1815875 (The Pile)

Max Activating Token Index: 888

Text #8

Max Range: 1.2199. Min Range: -1.2199

Max Act: 0.8696. Min Act: -0.0000

Data Index: 900980 (The Pile)

Max Activating Token Index: 358

Text #9

Max Range: 1.2199. Min Range: -1.2199

Max Act: 0.9149. Min Act: -0.0000

Data Index: 500390 (The Pile)

Max Activating Token Index: 280

Text #10

Max Range: 1.2199. Min Range: -1.2199

Max Act: 0.8263. Min Act: -0.0000

Data Index: 1310340 (The Pile)

Max Activating Token Index: 165

Text #11

Max Range: 1.2199. Min Range: -1.2199

Max Act: 0.8303. Min Act: -0.0000

Data Index: 1257219 (The Pile)

Max Activating Token Index: 47

Text #12

Max Range: 1.2199. Min Range: -1.2199

Max Act: 0.8958. Min Act: -0.0000

Data Index: 926028 (The Pile)

Max Activating Token Index: 608

Text #13

Max Range: 1.2199. Min Range: -1.2199

Max Act: 0.7605. Min Act: -0.0000

Data Index: 843535 (The Pile)

Max Activating Token Index: 68

Text #14

Max Range: 1.2199. Min Range: -1.2199

Max Act: 0.7847. Min Act: -0.0000

Data Index: 272570 (The Pile)

Max Activating Token Index: 682

Text #15

Max Range: 1.2199. Min Range: -1.2199

Max Act: 0.8333. Min Act: -0.0000

Data Index: 35605 (The Pile)

Max Activating Token Index: 176

Text #16

Max Range: 1.2199. Min Range: -1.2199

Max Act: 0.7516. Min Act: -0.0000

Data Index: 1997107 (The Pile)

Max Activating Token Index: 53

Text #17

Max Range: 1.2199. Min Range: -1.2199

Max Act: 0.7686. Min Act: -0.0000

Data Index: 1200354 (The Pile)

Max Activating Token Index: 653

Text #18

Max Range: 1.2199. Min Range: -1.2199

Max Act: 0.8548. Min Act: -0.0000

Data Index: 1067430 (The Pile)

Max Activating Token Index: 204

Text #19

Max Range: 1.2199. Min Range: -1.2199

Max Act: 0.8177. Min Act: -0.0000

Data Index: 549771 (The Pile)

Max Activating Token Index: 461