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

Dataset: The Pile

Neuron 2355 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: 1.0039. Min Range: -1.0039

Max Act: 0.9538. Min Act: -0.0000

Data Index: 1328811 (The Pile)

Max Activating Token Index: 142

Text #1

Max Range: 1.0039. Min Range: -1.0039

Max Act: 0.9352. Min Act: -0.0000

Data Index: 1561505 (The Pile)

Max Activating Token Index: 860

Text #2

Max Range: 1.0039. Min Range: -1.0039

Max Act: 0.9736. Min Act: -0.0000

Data Index: 273005 (The Pile)

Max Activating Token Index: 428

Text #3

Max Range: 1.0039. Min Range: -1.0039

Max Act: 1.0039. Min Act: -0.0000

Data Index: 766003 (The Pile)

Max Activating Token Index: 628

Text #4

Max Range: 1.0039. Min Range: -1.0039

Max Act: 0.9446. Min Act: -0.0000

Data Index: 1790156 (The Pile)

Max Activating Token Index: 491

Text #5

Max Range: 1.0039. Min Range: -1.0039

Max Act: 0.8810. Min Act: -0.0000

Data Index: 1584964 (The Pile)

Max Activating Token Index: 635

Text #6

Max Range: 1.0039. Min Range: -1.0039

Max Act: 0.9744. Min Act: -0.0000

Data Index: 699391 (The Pile)

Max Activating Token Index: 832

Text #7

Max Range: 1.0039. Min Range: -1.0039

Max Act: 0.9236. Min Act: -0.0000

Data Index: 1564985 (The Pile)

Max Activating Token Index: 379

Text #8

Max Range: 1.0039. Min Range: -1.0039

Max Act: 0.9329. Min Act: -0.0000

Data Index: 1621771 (The Pile)

Max Activating Token Index: 223

Text #9

Max Range: 1.0039. Min Range: -1.0039

Max Act: 0.8910. Min Act: -0.0000

Data Index: 401663 (The Pile)

Max Activating Token Index: 644

Text #10

Max Range: 1.0039. Min Range: -1.0039

Max Act: 0.9143. Min Act: -0.0000

Data Index: 833988 (The Pile)

Max Activating Token Index: 194

Text #11

Max Range: 1.0039. Min Range: -1.0039

Max Act: 0.7925. Min Act: -0.0000

Data Index: 1685507 (The Pile)

Max Activating Token Index: 153

Text #12

Max Range: 1.0039. Min Range: -1.0039

Max Act: 0.7779. Min Act: -0.0000

Data Index: 740639 (The Pile)

Max Activating Token Index: 738

Text #13

Max Range: 1.0039. Min Range: -1.0039

Max Act: 0.8223. Min Act: -0.0000

Data Index: 1741379 (The Pile)

Max Activating Token Index: 260

Text #14

Max Range: 1.0039. Min Range: -1.0039

Max Act: 0.7191. Min Act: -0.0000

Data Index: 961128 (The Pile)

Max Activating Token Index: 957

Text #15

Max Range: 1.0039. Min Range: -1.0039

Max Act: 0.7980. Min Act: -0.0000

Data Index: 1854306 (The Pile)

Max Activating Token Index: 250

Text #16

Max Range: 1.0039. Min Range: -1.0039

Max Act: 0.8576. Min Act: -0.0000

Data Index: 297796 (The Pile)

Max Activating Token Index: 895

Text #17

Max Range: 1.0039. Min Range: -1.0039

Max Act: 0.7117. Min Act: -0.0000

Data Index: 1802937 (The Pile)

Max Activating Token Index: 466

Text #18

Max Range: 1.0039. Min Range: -1.0039

Max Act: 0.7237. Min Act: -0.0000

Data Index: 1076095 (The Pile)

Max Activating Token Index: 710

Text #19

Max Range: 1.0039. Min Range: -1.0039

Max Act: 0.7473. Min Act: -0.0000

Data Index: 840304 (The Pile)

Max Activating Token Index: 486