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

Dataset: The Pile

Neuron 4059 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: 1.3285. Min Range: -1.3285

Max Act: 1.3285. Min Act: -0.0000

Data Index: 1386545 (The Pile)

Max Activating Token Index: 258

Text #1

Max Range: 1.3285. Min Range: -1.3285

Max Act: 1.0169. Min Act: -0.0000

Data Index: 1730281 (The Pile)

Max Activating Token Index: 913

Text #2

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.9740. Min Act: -0.0000

Data Index: 785353 (The Pile)

Max Activating Token Index: 690

Text #3

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.9397. Min Act: -0.0000

Data Index: 1390048 (The Pile)

Max Activating Token Index: 208

Text #4

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.9145. Min Act: -0.0000

Data Index: 1188690 (The Pile)

Max Activating Token Index: 91

Text #5

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.9686. Min Act: -0.0000

Data Index: 193309 (The Pile)

Max Activating Token Index: 281

Text #6

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.8446. Min Act: -0.0000

Data Index: 544416 (The Pile)

Max Activating Token Index: 600

Text #7

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.7801. Min Act: -0.0000

Data Index: 138400 (The Pile)

Max Activating Token Index: 559

Text #8

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.6445. Min Act: -0.0000

Data Index: 1180143 (The Pile)

Max Activating Token Index: 1010

Text #9

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.7755. Min Act: -0.0000

Data Index: 138786 (The Pile)

Max Activating Token Index: 390

Text #10

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.7489. Min Act: -0.0000

Data Index: 1960743 (The Pile)

Max Activating Token Index: 557

Text #11

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.7529. Min Act: -0.0000

Data Index: 1117425 (The Pile)

Max Activating Token Index: 152

Text #12

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.7229. Min Act: -0.0000

Data Index: 671644 (The Pile)

Max Activating Token Index: 254

Text #13

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.6850. Min Act: -0.0000

Data Index: 710289 (The Pile)

Max Activating Token Index: 1003

Text #14

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.8068. Min Act: -0.0000

Data Index: 1666675 (The Pile)

Max Activating Token Index: 555

Text #15

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.6923. Min Act: -0.0000

Data Index: 1044945 (The Pile)

Max Activating Token Index: 448

Text #16

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.6664. Min Act: -0.0000

Data Index: 1181862 (The Pile)

Max Activating Token Index: 468

Text #17

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.6782. Min Act: -0.0000

Data Index: 35682 (The Pile)

Max Activating Token Index: 409

Text #18

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.6506. Min Act: -0.0000

Data Index: 1506283 (The Pile)

Max Activating Token Index: 421

Text #19

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.5616. Min Act: -0.0000

Data Index: 368364 (The Pile)

Max Activating Token Index: 197