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

Dataset: The Pile

Neuron 2783 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7606. Min Range: -5.7606

Max Act: 5.7606. Min Act: -0.0000

Data Index: 839830 (The Pile)

Max Activating Token Index: 737

Text #1

Max Range: 5.7606. Min Range: -5.7606

Max Act: 5.5276. Min Act: -0.0000

Data Index: 1175681 (The Pile)

Max Activating Token Index: 343

Text #2

Max Range: 5.7606. Min Range: -5.7606

Max Act: 5.5251. Min Act: -0.0000

Data Index: 1085397 (The Pile)

Max Activating Token Index: 434

Text #3

Max Range: 5.7606. Min Range: -5.7606

Max Act: 5.1922. Min Act: -0.0000

Data Index: 1864293 (The Pile)

Max Activating Token Index: 394

Text #4

Max Range: 5.7606. Min Range: -5.7606

Max Act: 5.1717. Min Act: -0.0000

Data Index: 1235092 (The Pile)

Max Activating Token Index: 344

Text #5

Max Range: 5.7606. Min Range: -5.7606

Max Act: 5.0150. Min Act: -0.0000

Data Index: 1834502 (The Pile)

Max Activating Token Index: 185

Text #6

Max Range: 5.7606. Min Range: -5.7606

Max Act: 4.6126. Min Act: -0.0000

Data Index: 1480503 (The Pile)

Max Activating Token Index: 422

Text #7

Max Range: 5.7606. Min Range: -5.7606

Max Act: 4.8829. Min Act: -0.0000

Data Index: 17378 (The Pile)

Max Activating Token Index: 931

Text #8

Max Range: 5.7606. Min Range: -5.7606

Max Act: 4.4395. Min Act: -0.0000

Data Index: 1033831 (The Pile)

Max Activating Token Index: 218

Text #9

Max Range: 5.7606. Min Range: -5.7606

Max Act: 5.0864. Min Act: -0.0000

Data Index: 1619172 (The Pile)

Max Activating Token Index: 434

Text #10

Max Range: 5.7606. Min Range: -5.7606

Max Act: 5.2260. Min Act: -0.0000

Data Index: 802675 (The Pile)

Max Activating Token Index: 214

Text #11

Max Range: 5.7606. Min Range: -5.7606

Max Act: 5.2072. Min Act: -0.0000

Data Index: 1007853 (The Pile)

Max Activating Token Index: 172

Text #12

Max Range: 5.7606. Min Range: -5.7606

Max Act: 4.6377. Min Act: -0.0000

Data Index: 714391 (The Pile)

Max Activating Token Index: 494

Text #13

Max Range: 5.7606. Min Range: -5.7606

Max Act: 4.9164. Min Act: -0.0000

Data Index: 1017886 (The Pile)

Max Activating Token Index: 326

Text #14

Max Range: 5.7606. Min Range: -5.7606

Max Act: 4.5617. Min Act: -0.0000

Data Index: 987775 (The Pile)

Max Activating Token Index: 910

Text #15

Max Range: 5.7606. Min Range: -5.7606

Max Act: 5.0158. Min Act: -0.0000

Data Index: 702780 (The Pile)

Max Activating Token Index: 761

Text #16

Max Range: 5.7606. Min Range: -5.7606

Max Act: 5.0161. Min Act: -0.0000

Data Index: 476903 (The Pile)

Max Activating Token Index: 427

Text #17

Max Range: 5.7606. Min Range: -5.7606

Max Act: 4.6254. Min Act: -0.0000

Data Index: 1484797 (The Pile)

Max Activating Token Index: 527

Text #18

Max Range: 5.7606. Min Range: -5.7606

Max Act: 4.8062. Min Act: -0.0000

Data Index: 715090 (The Pile)

Max Activating Token Index: 659

Text #19

Max Range: 5.7606. Min Range: -5.7606

Max Act: 4.7563. Min Act: -0.0000

Data Index: 1775713 (The Pile)

Max Activating Token Index: 911