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

Dataset: The Pile

Neuron 3863 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: 1.2624. Min Range: -1.2624

Max Act: 1.2624. Min Act: -0.0000

Data Index: 1968308 (The Pile)

Max Activating Token Index: 124

Text #1

Max Range: 1.2624. Min Range: -1.2624

Max Act: 1.2185. Min Act: -0.0000

Data Index: 1714695 (The Pile)

Max Activating Token Index: 343

Text #2

Max Range: 1.2624. Min Range: -1.2624

Max Act: 1.1811. Min Act: -0.0000

Data Index: 1119178 (The Pile)

Max Activating Token Index: 1014

Text #3

Max Range: 1.2624. Min Range: -1.2624

Max Act: 1.1674. Min Act: -0.0000

Data Index: 1613430 (The Pile)

Max Activating Token Index: 999

Text #4

Max Range: 1.2624. Min Range: -1.2624

Max Act: 1.2621. Min Act: -0.0000

Data Index: 169501 (The Pile)

Max Activating Token Index: 842

Text #5

Max Range: 1.2624. Min Range: -1.2624

Max Act: 1.0648. Min Act: -0.0000

Data Index: 1482229 (The Pile)

Max Activating Token Index: 84

Text #6

Max Range: 1.2624. Min Range: -1.2624

Max Act: 1.1741. Min Act: -0.0000

Data Index: 266418 (The Pile)

Max Activating Token Index: 772

Text #7

Max Range: 1.2624. Min Range: -1.2624

Max Act: 1.1226. Min Act: -0.0000

Data Index: 1262385 (The Pile)

Max Activating Token Index: 680

Text #8

Max Range: 1.2624. Min Range: -1.2624

Max Act: 1.0473. Min Act: -0.0000

Data Index: 1870064 (The Pile)

Max Activating Token Index: 204

Text #9

Max Range: 1.2624. Min Range: -1.2624

Max Act: 1.1086. Min Act: -0.0000

Data Index: 1358998 (The Pile)

Max Activating Token Index: 330

Text #10

Max Range: 1.2624. Min Range: -1.2624

Max Act: 1.0851. Min Act: -0.0000

Data Index: 165777 (The Pile)

Max Activating Token Index: 883

Text #11

Max Range: 1.2624. Min Range: -1.2624

Max Act: 1.0462. Min Act: -0.0000

Data Index: 31431 (The Pile)

Max Activating Token Index: 303

Text #12

Max Range: 1.2624. Min Range: -1.2624

Max Act: 1.0963. Min Act: -0.0000

Data Index: 1240405 (The Pile)

Max Activating Token Index: 1006

Text #13

Max Range: 1.2624. Min Range: -1.2624

Max Act: 1.0826. Min Act: -0.0000

Data Index: 707710 (The Pile)

Max Activating Token Index: 222

Text #14

Max Range: 1.2624. Min Range: -1.2624

Max Act: 1.0116. Min Act: -0.0000

Data Index: 1983021 (The Pile)

Max Activating Token Index: 853

Text #15

Max Range: 1.2624. Min Range: -1.2624

Max Act: 1.0395. Min Act: -0.0000

Data Index: 946891 (The Pile)

Max Activating Token Index: 818

Text #16

Max Range: 1.2624. Min Range: -1.2624

Max Act: 1.0779. Min Act: -0.0000

Data Index: 1331186 (The Pile)

Max Activating Token Index: 840

Text #17

Max Range: 1.2624. Min Range: -1.2624

Max Act: 1.0018. Min Act: -0.0000

Data Index: 1615489 (The Pile)

Max Activating Token Index: 501

Text #18

Max Range: 1.2624. Min Range: -1.2624

Max Act: 1.0222. Min Act: -0.0000

Data Index: 1812226 (The Pile)

Max Activating Token Index: 241

Text #19

Max Range: 1.2624. Min Range: -1.2624

Max Act: 1.0535. Min Act: -0.0000

Data Index: 1483675 (The Pile)

Max Activating Token Index: 108