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

Dataset: The Pile

Neuron 3510 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.8773. Min Act: -0.0000

Data Index: 1499369 (The Pile)

Max Activating Token Index: 434

Text #1

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.9015. Min Act: -0.0000

Data Index: 1511256 (The Pile)

Max Activating Token Index: 673

Text #2

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.9292. Min Act: -0.0000

Data Index: 1497116 (The Pile)

Max Activating Token Index: 825

Text #3

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.8211. Min Act: -0.0000

Data Index: 771822 (The Pile)

Max Activating Token Index: 997

Text #4

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.7419. Min Act: -0.0000

Data Index: 1943038 (The Pile)

Max Activating Token Index: 350

Text #5

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.8148. Min Act: -0.0000

Data Index: 162420 (The Pile)

Max Activating Token Index: 136

Text #6

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.7428. Min Act: -0.0000

Data Index: 675408 (The Pile)

Max Activating Token Index: 45

Text #7

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.7239. Min Act: -0.0000

Data Index: 1851021 (The Pile)

Max Activating Token Index: 992

Text #8

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.7054. Min Act: -0.0000

Data Index: 883052 (The Pile)

Max Activating Token Index: 890

Text #9

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.6822. Min Act: -0.0000

Data Index: 639175 (The Pile)

Max Activating Token Index: 1015

Text #10

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.6175. Min Act: -0.0000

Data Index: 1206494 (The Pile)

Max Activating Token Index: 758

Text #11

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.6280. Min Act: -0.0000

Data Index: 175304 (The Pile)

Max Activating Token Index: 788

Text #12

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.6750. Min Act: -0.0000

Data Index: 630577 (The Pile)

Max Activating Token Index: 371

Text #13

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.7072. Min Act: -0.0000

Data Index: 1893951 (The Pile)

Max Activating Token Index: 339

Text #14

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.6816. Min Act: -0.0000

Data Index: 138789 (The Pile)

Max Activating Token Index: 306

Text #15

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.6670. Min Act: -0.0000

Data Index: 1753360 (The Pile)

Max Activating Token Index: 186

Text #16

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.6805. Min Act: -0.0000

Data Index: 1273052 (The Pile)

Max Activating Token Index: 34

Text #17

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.6213. Min Act: -0.0000

Data Index: 1872851 (The Pile)

Max Activating Token Index: 603

Text #18

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.6218. Min Act: -0.0000

Data Index: 398320 (The Pile)

Max Activating Token Index: 709

Text #19

Max Range: 0.9292. Min Range: -0.9292

Max Act: 0.6365. Min Act: -0.0000

Data Index: 784150 (The Pile)

Max Activating Token Index: 253