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

Dataset: The Pile

Neuron 4792 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: 5.8739. Min Range: -5.8739

Max Act: 5.8739. Min Act: -0.0000

Data Index: 1770841 (The Pile)

Max Activating Token Index: 538

Text #1

Max Range: 5.8739. Min Range: -5.8739

Max Act: 5.5103. Min Act: -0.0000

Data Index: 1757654 (The Pile)

Max Activating Token Index: 409

Text #2

Max Range: 5.8739. Min Range: -5.8739

Max Act: 5.2767. Min Act: -0.0000

Data Index: 1347201 (The Pile)

Max Activating Token Index: 730

Text #3

Max Range: 5.8739. Min Range: -5.8739

Max Act: 5.1071. Min Act: -0.0000

Data Index: 1260408 (The Pile)

Max Activating Token Index: 623

Text #4

Max Range: 5.8739. Min Range: -5.8739

Max Act: 4.7283. Min Act: -0.0000

Data Index: 1745962 (The Pile)

Max Activating Token Index: 568

Text #5

Max Range: 5.8739. Min Range: -5.8739

Max Act: 4.9084. Min Act: -0.0000

Data Index: 657307 (The Pile)

Max Activating Token Index: 635

Text #6

Max Range: 5.8739. Min Range: -5.8739

Max Act: 4.1603. Min Act: -0.0000

Data Index: 1938788 (The Pile)

Max Activating Token Index: 558

Text #7

Max Range: 5.8739. Min Range: -5.8739

Max Act: 4.6609. Min Act: -0.0000

Data Index: 1732275 (The Pile)

Max Activating Token Index: 369

Text #8

Max Range: 5.8739. Min Range: -5.8739

Max Act: 4.4892. Min Act: -0.0000

Data Index: 27237 (The Pile)

Max Activating Token Index: 308

Text #9

Max Range: 5.8739. Min Range: -5.8739

Max Act: 3.8362. Min Act: -0.0000

Data Index: 1098203 (The Pile)

Max Activating Token Index: 1010

Text #10

Max Range: 5.8739. Min Range: -5.8739

Max Act: 4.9540. Min Act: -0.0000

Data Index: 576882 (The Pile)

Max Activating Token Index: 221

Text #11

Max Range: 5.8739. Min Range: -5.8739

Max Act: 4.4535. Min Act: -0.0000

Data Index: 24119 (The Pile)

Max Activating Token Index: 619

Text #12

Max Range: 5.8739. Min Range: -5.8739

Max Act: 4.6115. Min Act: -0.0000

Data Index: 1445678 (The Pile)

Max Activating Token Index: 247

Text #13

Max Range: 5.8739. Min Range: -5.8739

Max Act: 4.8488. Min Act: -0.0000

Data Index: 1840044 (The Pile)

Max Activating Token Index: 793

Text #14

Max Range: 5.8739. Min Range: -5.8739

Max Act: 4.5474. Min Act: -0.0000

Data Index: 1361107 (The Pile)

Max Activating Token Index: 595

Text #15

Max Range: 5.8739. Min Range: -5.8739

Max Act: 4.1614. Min Act: -0.0000

Data Index: 1617714 (The Pile)

Max Activating Token Index: 877

Text #16

Max Range: 5.8739. Min Range: -5.8739

Max Act: 4.3104. Min Act: -0.0000

Data Index: 1313702 (The Pile)

Max Activating Token Index: 90

Text #17

Max Range: 5.8739. Min Range: -5.8739

Max Act: 4.1340. Min Act: -0.0000

Data Index: 1561531 (The Pile)

Max Activating Token Index: 727

Text #18

Max Range: 5.8739. Min Range: -5.8739

Max Act: 3.6962. Min Act: -0.0000

Data Index: 16166 (The Pile)

Max Activating Token Index: 391

Text #19

Max Range: 5.8739. Min Range: -5.8739

Max Act: 4.0305. Min Act: -0.0000

Data Index: 959070 (The Pile)

Max Activating Token Index: 70