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

Dataset: The Pile

Neuron 145 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: 1.1716. Min Range: -1.1716

Max Act: 1.1716. Min Act: -0.0000

Data Index: 1351964 (The Pile)

Max Activating Token Index: 324

Text #1

Max Range: 1.1716. Min Range: -1.1716

Max Act: 1.0604. Min Act: -0.0000

Data Index: 224859 (The Pile)

Max Activating Token Index: 393

Text #2

Max Range: 1.1716. Min Range: -1.1716

Max Act: 1.0684. Min Act: -0.0000

Data Index: 1563696 (The Pile)

Max Activating Token Index: 663

Text #3

Max Range: 1.1716. Min Range: -1.1716

Max Act: 0.9044. Min Act: -0.0000

Data Index: 1743968 (The Pile)

Max Activating Token Index: 577

Text #4

Max Range: 1.1716. Min Range: -1.1716

Max Act: 1.0185. Min Act: -0.0000

Data Index: 1648033 (The Pile)

Max Activating Token Index: 441

Text #5

Max Range: 1.1716. Min Range: -1.1716

Max Act: 0.9737. Min Act: -0.0000

Data Index: 1210996 (The Pile)

Max Activating Token Index: 979

Text #6

Max Range: 1.1716. Min Range: -1.1716

Max Act: 0.9579. Min Act: -0.0000

Data Index: 1908918 (The Pile)

Max Activating Token Index: 890

Text #7

Max Range: 1.1716. Min Range: -1.1716

Max Act: 1.0372. Min Act: -0.0000

Data Index: 857008 (The Pile)

Max Activating Token Index: 381

Text #8

Max Range: 1.1716. Min Range: -1.1716

Max Act: 1.0214. Min Act: -0.0000

Data Index: 268503 (The Pile)

Max Activating Token Index: 818

Text #9

Max Range: 1.1716. Min Range: -1.1716

Max Act: 1.0309. Min Act: -0.0000

Data Index: 161561 (The Pile)

Max Activating Token Index: 449

Text #10

Max Range: 1.1716. Min Range: -1.1716

Max Act: 1.0558. Min Act: -0.0000

Data Index: 1376531 (The Pile)

Max Activating Token Index: 446

Text #11

Max Range: 1.1716. Min Range: -1.1716

Max Act: 0.9879. Min Act: -0.0000

Data Index: 1181649 (The Pile)

Max Activating Token Index: 589

Text #12

Max Range: 1.1716. Min Range: -1.1716

Max Act: 1.0323. Min Act: -0.0000

Data Index: 614225 (The Pile)

Max Activating Token Index: 73

Text #13

Max Range: 1.1716. Min Range: -1.1716

Max Act: 1.0812. Min Act: -0.0000

Data Index: 1805945 (The Pile)

Max Activating Token Index: 902

Text #14

Max Range: 1.1716. Min Range: -1.1716

Max Act: 0.8838. Min Act: -0.0000

Data Index: 1944425 (The Pile)

Max Activating Token Index: 440

Text #15

Max Range: 1.1716. Min Range: -1.1716

Max Act: 0.9261. Min Act: -0.0000

Data Index: 1873126 (The Pile)

Max Activating Token Index: 186

Text #16

Max Range: 1.1716. Min Range: -1.1716

Max Act: 0.8422. Min Act: -0.0000

Data Index: 1029716 (The Pile)

Max Activating Token Index: 723

Text #17

Max Range: 1.1716. Min Range: -1.1716

Max Act: 0.9480. Min Act: -0.0000

Data Index: 1468062 (The Pile)

Max Activating Token Index: 493

Text #18

Max Range: 1.1716. Min Range: -1.1716

Max Act: 0.8850. Min Act: -0.0000

Data Index: 1621610 (The Pile)

Max Activating Token Index: 300

Text #19

Max Range: 1.1716. Min Range: -1.1716

Max Act: 0.8585. Min Act: -0.0000

Data Index: 689818 (The Pile)

Max Activating Token Index: 568