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

Dataset: The Pile

Neuron 3856 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9754. Min Range: -3.9754

Max Act: 3.9754. Min Act: -0.0000

Data Index: 296194 (The Pile)

Max Activating Token Index: 821

Text #1

Max Range: 3.9754. Min Range: -3.9754

Max Act: 3.8491. Min Act: -0.0000

Data Index: 164619 (The Pile)

Max Activating Token Index: 15

Text #2

Max Range: 3.9754. Min Range: -3.9754

Max Act: 3.4290. Min Act: -0.0000

Data Index: 1784210 (The Pile)

Max Activating Token Index: 734

Text #3

Max Range: 3.9754. Min Range: -3.9754

Max Act: 3.2597. Min Act: -0.0000

Data Index: 1129432 (The Pile)

Max Activating Token Index: 42

Text #4

Max Range: 3.9754. Min Range: -3.9754

Max Act: 3.1258. Min Act: -0.0000

Data Index: 1245928 (The Pile)

Max Activating Token Index: 756

Text #5

Max Range: 3.9754. Min Range: -3.9754

Max Act: 2.8817. Min Act: -0.0000

Data Index: 396340 (The Pile)

Max Activating Token Index: 427

Text #6

Max Range: 3.9754. Min Range: -3.9754

Max Act: 2.6893. Min Act: -0.0000

Data Index: 1847122 (The Pile)

Max Activating Token Index: 834

Text #7

Max Range: 3.9754. Min Range: -3.9754

Max Act: 3.0800. Min Act: -0.0000

Data Index: 1994234 (The Pile)

Max Activating Token Index: 109

Text #8

Max Range: 3.9754. Min Range: -3.9754

Max Act: 2.7491. Min Act: -0.0000

Data Index: 216490 (The Pile)

Max Activating Token Index: 667

Text #9

Max Range: 3.9754. Min Range: -3.9754

Max Act: 2.8206. Min Act: -0.0000

Data Index: 1506977 (The Pile)

Max Activating Token Index: 51

Text #10

Max Range: 3.9754. Min Range: -3.9754

Max Act: 2.7751. Min Act: -0.0000

Data Index: 1495462 (The Pile)

Max Activating Token Index: 231

Text #11

Max Range: 3.9754. Min Range: -3.9754

Max Act: 2.8081. Min Act: -0.0000

Data Index: 607142 (The Pile)

Max Activating Token Index: 407

Text #12

Max Range: 3.9754. Min Range: -3.9754

Max Act: 2.6350. Min Act: -0.0000

Data Index: 130873 (The Pile)

Max Activating Token Index: 603

Text #13

Max Range: 3.9754. Min Range: -3.9754

Max Act: 2.6128. Min Act: -0.0000

Data Index: 877690 (The Pile)

Max Activating Token Index: 764

Text #14

Max Range: 3.9754. Min Range: -3.9754

Max Act: 2.6935. Min Act: -0.0000

Data Index: 438224 (The Pile)

Max Activating Token Index: 23

Text #15

Max Range: 3.9754. Min Range: -3.9754

Max Act: 2.6478. Min Act: -0.0000

Data Index: 115655 (The Pile)

Max Activating Token Index: 722

Text #16

Max Range: 3.9754. Min Range: -3.9754

Max Act: 2.6602. Min Act: -0.0000

Data Index: 975965 (The Pile)

Max Activating Token Index: 750

Text #17

Max Range: 3.9754. Min Range: -3.9754

Max Act: 2.5998. Min Act: -0.0000

Data Index: 1551893 (The Pile)

Max Activating Token Index: 152

Text #18

Max Range: 3.9754. Min Range: -3.9754

Max Act: 2.5455. Min Act: -0.0000

Data Index: 1018801 (The Pile)

Max Activating Token Index: 413

Text #19

Max Range: 3.9754. Min Range: -3.9754

Max Act: 2.5171. Min Act: -0.0000

Data Index: 909120 (The Pile)

Max Activating Token Index: 469