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

Dataset: The Pile

Neuron 4152 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0600. Min Range: -1.0600

Max Act: 1.0600. Min Act: -0.0000

Data Index: 937870 (The Pile)

Max Activating Token Index: 124

Text #1

Max Range: 1.0600. Min Range: -1.0600

Max Act: 1.0237. Min Act: -0.0000

Data Index: 306301 (The Pile)

Max Activating Token Index: 699

Text #2

Max Range: 1.0600. Min Range: -1.0600

Max Act: 0.8913. Min Act: -0.0000

Data Index: 331440 (The Pile)

Max Activating Token Index: 171

Text #3

Max Range: 1.0600. Min Range: -1.0600

Max Act: 0.8375. Min Act: -0.0000

Data Index: 963332 (The Pile)

Max Activating Token Index: 77

Text #4

Max Range: 1.0600. Min Range: -1.0600

Max Act: 0.9170. Min Act: -0.0000

Data Index: 1149135 (The Pile)

Max Activating Token Index: 582

Text #5

Max Range: 1.0600. Min Range: -1.0600

Max Act: 0.9418. Min Act: -0.0000

Data Index: 102141 (The Pile)

Max Activating Token Index: 706

Text #6

Max Range: 1.0600. Min Range: -1.0600

Max Act: 0.8657. Min Act: -0.0000

Data Index: 1328539 (The Pile)

Max Activating Token Index: 647

Text #7

Max Range: 1.0600. Min Range: -1.0600

Max Act: 0.8838. Min Act: -0.0000

Data Index: 1093392 (The Pile)

Max Activating Token Index: 777

Text #8

Max Range: 1.0600. Min Range: -1.0600

Max Act: 0.8760. Min Act: -0.0000

Data Index: 524726 (The Pile)

Max Activating Token Index: 1012

Text #9

Max Range: 1.0600. Min Range: -1.0600

Max Act: 0.8338. Min Act: -0.0000

Data Index: 853390 (The Pile)

Max Activating Token Index: 200

Text #10

Max Range: 1.0600. Min Range: -1.0600

Max Act: 0.8232. Min Act: -0.0000

Data Index: 1440035 (The Pile)

Max Activating Token Index: 597

Text #11

Max Range: 1.0600. Min Range: -1.0600

Max Act: 0.8255. Min Act: -0.0000

Data Index: 1205497 (The Pile)

Max Activating Token Index: 636

Text #12

Max Range: 1.0600. Min Range: -1.0600

Max Act: 0.7925. Min Act: -0.0000

Data Index: 1892862 (The Pile)

Max Activating Token Index: 507

Text #13

Max Range: 1.0600. Min Range: -1.0600

Max Act: 0.7875. Min Act: -0.0000

Data Index: 693566 (The Pile)

Max Activating Token Index: 383

Text #14

Max Range: 1.0600. Min Range: -1.0600

Max Act: 0.7355. Min Act: -0.0000

Data Index: 670574 (The Pile)

Max Activating Token Index: 260

Text #15

Max Range: 1.0600. Min Range: -1.0600

Max Act: 0.8006. Min Act: -0.0000

Data Index: 178367 (The Pile)

Max Activating Token Index: 588

Text #16

Max Range: 1.0600. Min Range: -1.0600

Max Act: 0.7712. Min Act: -0.0000

Data Index: 1165917 (The Pile)

Max Activating Token Index: 780

Text #17

Max Range: 1.0600. Min Range: -1.0600

Max Act: 0.7134. Min Act: -0.0000

Data Index: 1929293 (The Pile)

Max Activating Token Index: 930

Text #18

Max Range: 1.0600. Min Range: -1.0600

Max Act: 0.7036. Min Act: -0.0000

Data Index: 1608842 (The Pile)

Max Activating Token Index: 554

Text #19

Max Range: 1.0600. Min Range: -1.0600

Max Act: 0.7409. Min Act: -0.0000

Data Index: 1610458 (The Pile)

Max Activating Token Index: 9