Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 331 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.7715. Min Act: -0.0000

Data Index: 1208750 (The Pile)

Max Activating Token Index: 949

Text #1

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.7347. Min Act: -0.0000

Data Index: 350794 (The Pile)

Max Activating Token Index: 163

Text #2

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.7111. Min Act: -0.0000

Data Index: 743851 (The Pile)

Max Activating Token Index: 579

Text #3

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.7630. Min Act: 0.0000

Data Index: 1484344 (The Pile)

Max Activating Token Index: 1014

Text #4

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.7564. Min Act: -0.0000

Data Index: 1958127 (The Pile)

Max Activating Token Index: 401

Text #5

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.7082. Min Act: -0.0000

Data Index: 1417777 (The Pile)

Max Activating Token Index: 998

Text #6

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.7541. Min Act: -0.0000

Data Index: 908449 (The Pile)

Max Activating Token Index: 732

Text #7

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.6373. Min Act: -0.0000

Data Index: 863277 (The Pile)

Max Activating Token Index: 589

Text #8

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.6595. Min Act: -0.0000

Data Index: 948215 (The Pile)

Max Activating Token Index: 816

Text #9

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.6838. Min Act: 0.0000

Data Index: 461675 (The Pile)

Max Activating Token Index: 624

Text #10

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.6204. Min Act: -0.0000

Data Index: 1824061 (The Pile)

Max Activating Token Index: 684

Text #11

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.7234. Min Act: -0.0000

Data Index: 1825104 (The Pile)

Max Activating Token Index: 430

Text #12

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.6555. Min Act: -0.0000

Data Index: 1564621 (The Pile)

Max Activating Token Index: 645

Text #13

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.5588. Min Act: -0.0000

Data Index: 1489700 (The Pile)

Max Activating Token Index: 670

Text #14

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.6804. Min Act: -0.0000

Data Index: 1789816 (The Pile)

Max Activating Token Index: 732

Text #15

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.6505. Min Act: -0.0000

Data Index: 613100 (The Pile)

Max Activating Token Index: 817

Text #16

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.6147. Min Act: -0.0000

Data Index: 923822 (The Pile)

Max Activating Token Index: 953

Text #17

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.5918. Min Act: -0.0000

Data Index: 186269 (The Pile)

Max Activating Token Index: 840

Text #18

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.5571. Min Act: -0.0000

Data Index: 47106 (The Pile)

Max Activating Token Index: 957

Text #19

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.5569. Min Act: -0.0000

Data Index: 824968 (The Pile)

Max Activating Token Index: 766