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

Dataset: The Pile

Neuron 982 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: 0.4661. Min Range: -0.4661

Max Act: 0.4621. Min Act: -0.0000

Data Index: 667369 (The Pile)

Max Activating Token Index: 567

Text #1

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.4452. Min Act: -0.0000

Data Index: 469820 (The Pile)

Max Activating Token Index: 118

Text #2

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.4257. Min Act: -0.0000

Data Index: 840670 (The Pile)

Max Activating Token Index: 33

Text #3

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.4052. Min Act: -0.0000

Data Index: 1010420 (The Pile)

Max Activating Token Index: 869

Text #4

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.4661. Min Act: -0.0000

Data Index: 649774 (The Pile)

Max Activating Token Index: 811

Text #5

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.3642. Min Act: -0.0000

Data Index: 745416 (The Pile)

Max Activating Token Index: 920

Text #6

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.3876. Min Act: -0.0000

Data Index: 954606 (The Pile)

Max Activating Token Index: 28

Text #7

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.4519. Min Act: -0.0000

Data Index: 1273891 (The Pile)

Max Activating Token Index: 570

Text #8

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.3896. Min Act: -0.0000

Data Index: 1651585 (The Pile)

Max Activating Token Index: 516

Text #9

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.3808. Min Act: -0.0000

Data Index: 209356 (The Pile)

Max Activating Token Index: 225

Text #10

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.4082. Min Act: -0.0000

Data Index: 502178 (The Pile)

Max Activating Token Index: 508

Text #11

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.3637. Min Act: -0.0000

Data Index: 1504525 (The Pile)

Max Activating Token Index: 839

Text #12

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.3365. Min Act: -0.0000

Data Index: 609976 (The Pile)

Max Activating Token Index: 823

Text #13

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.3783. Min Act: -0.0000

Data Index: 1201450 (The Pile)

Max Activating Token Index: 908

Text #14

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.3889. Min Act: -0.0000

Data Index: 400449 (The Pile)

Max Activating Token Index: 344

Text #15

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.3761. Min Act: -0.0000

Data Index: 851517 (The Pile)

Max Activating Token Index: 648

Text #16

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.3484. Min Act: -0.0000

Data Index: 251560 (The Pile)

Max Activating Token Index: 907

Text #17

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.3543. Min Act: -0.0000

Data Index: 1341288 (The Pile)

Max Activating Token Index: 150

Text #18

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.3768. Min Act: -0.0000

Data Index: 697638 (The Pile)

Max Activating Token Index: 769

Text #19

Max Range: 0.4661. Min Range: -0.4661

Max Act: 0.3265. Min Act: -0.0000

Data Index: 1680286 (The Pile)

Max Activating Token Index: 213