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

Dataset: The Pile

Neuron 3988 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: 3.2692. Min Range: -3.2692

Max Act: 3.2649. Min Act: -0.0000

Data Index: 1355739 (The Pile)

Max Activating Token Index: 644

Text #1

Max Range: 3.2692. Min Range: -3.2692

Max Act: 3.0663. Min Act: -0.0000

Data Index: 600369 (The Pile)

Max Activating Token Index: 678

Text #2

Max Range: 3.2692. Min Range: -3.2692

Max Act: 3.0057. Min Act: -0.0000

Data Index: 709159 (The Pile)

Max Activating Token Index: 901

Text #3

Max Range: 3.2692. Min Range: -3.2692

Max Act: 3.2692. Min Act: -0.0000

Data Index: 134178 (The Pile)

Max Activating Token Index: 319

Text #4

Max Range: 3.2692. Min Range: -3.2692

Max Act: 2.9645. Min Act: -0.0000

Data Index: 1265507 (The Pile)

Max Activating Token Index: 641

Text #5

Max Range: 3.2692. Min Range: -3.2692

Max Act: 2.9563. Min Act: -0.0000

Data Index: 141803 (The Pile)

Max Activating Token Index: 1005

Text #6

Max Range: 3.2692. Min Range: -3.2692

Max Act: 2.9958. Min Act: -0.0000

Data Index: 1800655 (The Pile)

Max Activating Token Index: 798

Text #7

Max Range: 3.2692. Min Range: -3.2692

Max Act: 2.9469. Min Act: -0.0000

Data Index: 1114961 (The Pile)

Max Activating Token Index: 198

Text #8

Max Range: 3.2692. Min Range: -3.2692

Max Act: 2.9301. Min Act: -0.0000

Data Index: 782727 (The Pile)

Max Activating Token Index: 597

Text #9

Max Range: 3.2692. Min Range: -3.2692

Max Act: 2.7818. Min Act: -0.0000

Data Index: 282969 (The Pile)

Max Activating Token Index: 678

Text #10

Max Range: 3.2692. Min Range: -3.2692

Max Act: 2.8855. Min Act: -0.0000

Data Index: 1447332 (The Pile)

Max Activating Token Index: 832

Text #11

Max Range: 3.2692. Min Range: -3.2692

Max Act: 2.8915. Min Act: -0.0000

Data Index: 363670 (The Pile)

Max Activating Token Index: 731

Text #12

Max Range: 3.2692. Min Range: -3.2692

Max Act: 2.7340. Min Act: -0.0000

Data Index: 1770918 (The Pile)

Max Activating Token Index: 623

Text #13

Max Range: 3.2692. Min Range: -3.2692

Max Act: 2.8806. Min Act: -0.0000

Data Index: 674649 (The Pile)

Max Activating Token Index: 841

Text #14

Max Range: 3.2692. Min Range: -3.2692

Max Act: 2.7498. Min Act: -0.0000

Data Index: 958385 (The Pile)

Max Activating Token Index: 607

Text #15

Max Range: 3.2692. Min Range: -3.2692

Max Act: 2.6887. Min Act: -0.0000

Data Index: 1147444 (The Pile)

Max Activating Token Index: 763

Text #16

Max Range: 3.2692. Min Range: -3.2692

Max Act: 2.8018. Min Act: -0.0000

Data Index: 215719 (The Pile)

Max Activating Token Index: 999

Text #17

Max Range: 3.2692. Min Range: -3.2692

Max Act: 2.8247. Min Act: -0.0000

Data Index: 1182045 (The Pile)

Max Activating Token Index: 951

Text #18

Max Range: 3.2692. Min Range: -3.2692

Max Act: 2.7666. Min Act: -0.0000

Data Index: 1518902 (The Pile)

Max Activating Token Index: 1018

Text #19

Max Range: 3.2692. Min Range: -3.2692

Max Act: 2.7620. Min Act: -0.0000

Data Index: 1989801 (The Pile)

Max Activating Token Index: 339