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

Dataset: The Pile

Neuron 949 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.8018. Min Act: -0.0000

Data Index: 982725 (The Pile)

Max Activating Token Index: 936

Text #1

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.6905. Min Act: -0.0000

Data Index: 168088 (The Pile)

Max Activating Token Index: 674

Text #2

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.6265. Min Act: -0.0000

Data Index: 1728144 (The Pile)

Max Activating Token Index: 825

Text #3

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.6630. Min Act: -0.0000

Data Index: 469916 (The Pile)

Max Activating Token Index: 471

Text #4

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.6505. Min Act: -0.0000

Data Index: 142063 (The Pile)

Max Activating Token Index: 415

Text #5

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.6920. Min Act: -0.0000

Data Index: 1979310 (The Pile)

Max Activating Token Index: 901

Text #6

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.6640. Min Act: -0.0000

Data Index: 1644722 (The Pile)

Max Activating Token Index: 924

Text #7

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.5909. Min Act: -0.0000

Data Index: 738471 (The Pile)

Max Activating Token Index: 153

Text #8

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.5543. Min Act: -0.0000

Data Index: 281797 (The Pile)

Max Activating Token Index: 1008

Text #9

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.5773. Min Act: -0.0000

Data Index: 422762 (The Pile)

Max Activating Token Index: 757

Text #10

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.5932. Min Act: -0.0000

Data Index: 640321 (The Pile)

Max Activating Token Index: 967

Text #11

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.6126. Min Act: -0.0000

Data Index: 1300514 (The Pile)

Max Activating Token Index: 705

Text #12

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.6028. Min Act: -0.0000

Data Index: 95462 (The Pile)

Max Activating Token Index: 867

Text #13

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.5592. Min Act: -0.0000

Data Index: 1768532 (The Pile)

Max Activating Token Index: 380

Text #14

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.5995. Min Act: -0.0000

Data Index: 74370 (The Pile)

Max Activating Token Index: 511

Text #15

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.5588. Min Act: -0.0000

Data Index: 529428 (The Pile)

Max Activating Token Index: 403

Text #16

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.5754. Min Act: -0.0000

Data Index: 1703331 (The Pile)

Max Activating Token Index: 45

Text #17

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.5684. Min Act: -0.0000

Data Index: 943526 (The Pile)

Max Activating Token Index: 883

Text #18

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.5516. Min Act: -0.0000

Data Index: 1581734 (The Pile)

Max Activating Token Index: 685

Text #19

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.5408. Min Act: -0.0000

Data Index: 116794 (The Pile)

Max Activating Token Index: 574