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

Dataset: The Pile

Neuron 4734 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0754. Min Range: -1.0754

Max Act: 1.0754. Min Act: -0.0000

Data Index: 1210818 (The Pile)

Max Activating Token Index: 269

Text #1

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7370. Min Act: -0.0000

Data Index: 1932882 (The Pile)

Max Activating Token Index: 56

Text #2

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.9083. Min Act: -0.0000

Data Index: 1296603 (The Pile)

Max Activating Token Index: 999

Text #3

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.8011. Min Act: -0.0000

Data Index: 1623444 (The Pile)

Max Activating Token Index: 639

Text #4

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7708. Min Act: -0.0000

Data Index: 721137 (The Pile)

Max Activating Token Index: 176

Text #5

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.6874. Min Act: -0.0000

Data Index: 1955147 (The Pile)

Max Activating Token Index: 945

Text #6

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7517. Min Act: -0.0000

Data Index: 1927862 (The Pile)

Max Activating Token Index: 258

Text #7

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7791. Min Act: -0.0000

Data Index: 1789468 (The Pile)

Max Activating Token Index: 131

Text #8

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7408. Min Act: -0.0000

Data Index: 925351 (The Pile)

Max Activating Token Index: 750

Text #9

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7181. Min Act: -0.0000

Data Index: 1034673 (The Pile)

Max Activating Token Index: 62

Text #10

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.6145. Min Act: -0.0000

Data Index: 392696 (The Pile)

Max Activating Token Index: 42

Text #11

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.6764. Min Act: -0.0000

Data Index: 629433 (The Pile)

Max Activating Token Index: 819

Text #12

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7429. Min Act: -0.0000

Data Index: 1612869 (The Pile)

Max Activating Token Index: 157

Text #13

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.6945. Min Act: -0.0000

Data Index: 1939001 (The Pile)

Max Activating Token Index: 752

Text #14

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.6700. Min Act: -0.0000

Data Index: 556246 (The Pile)

Max Activating Token Index: 63

Text #15

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.6602. Min Act: -0.0000

Data Index: 156790 (The Pile)

Max Activating Token Index: 162

Text #16

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7199. Min Act: -0.0000

Data Index: 1862927 (The Pile)

Max Activating Token Index: 484

Text #17

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.6671. Min Act: -0.0000

Data Index: 1609575 (The Pile)

Max Activating Token Index: 118

Text #18

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.6624. Min Act: -0.0000

Data Index: 942842 (The Pile)

Max Activating Token Index: 99

Text #19

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.6795. Min Act: -0.0000

Data Index: 181774 (The Pile)

Max Activating Token Index: 556