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

Dataset: The Pile

Neuron 2486 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: 1.3913. Min Range: -1.3913

Max Act: 1.1153. Min Act: -0.0000

Data Index: 1387459 (The Pile)

Max Activating Token Index: 616

Text #1

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.3893. Min Act: -0.0000

Data Index: 13070 (The Pile)

Max Activating Token Index: 435

Text #2

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.3501. Min Act: -0.0000

Data Index: 1726298 (The Pile)

Max Activating Token Index: 793

Text #3

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.3913. Min Act: -0.0000

Data Index: 618641 (The Pile)

Max Activating Token Index: 30

Text #4

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.3104. Min Act: -0.0000

Data Index: 1841434 (The Pile)

Max Activating Token Index: 719

Text #5

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.3034. Min Act: -0.0000

Data Index: 679357 (The Pile)

Max Activating Token Index: 476

Text #6

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.2941. Min Act: -0.0000

Data Index: 1186588 (The Pile)

Max Activating Token Index: 820

Text #7

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.1273. Min Act: -0.0000

Data Index: 467987 (The Pile)

Max Activating Token Index: 202

Text #8

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.2004. Min Act: -0.0000

Data Index: 1376628 (The Pile)

Max Activating Token Index: 972

Text #9

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.3602. Min Act: -0.0000

Data Index: 1749977 (The Pile)

Max Activating Token Index: 1002

Text #10

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.2017. Min Act: -0.0000

Data Index: 610436 (The Pile)

Max Activating Token Index: 420

Text #11

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.1518. Min Act: -0.0000

Data Index: 828463 (The Pile)

Max Activating Token Index: 785

Text #12

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.0139. Min Act: -0.0000

Data Index: 1569238 (The Pile)

Max Activating Token Index: 863

Text #13

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.2015. Min Act: -0.0000

Data Index: 110959 (The Pile)

Max Activating Token Index: 917

Text #14

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.1396. Min Act: -0.0000

Data Index: 1862523 (The Pile)

Max Activating Token Index: 490

Text #15

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.2789. Min Act: -0.0000

Data Index: 142413 (The Pile)

Max Activating Token Index: 953

Text #16

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.1306. Min Act: -0.0000

Data Index: 1705318 (The Pile)

Max Activating Token Index: 157

Text #17

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.0465. Min Act: -0.0000

Data Index: 1912781 (The Pile)

Max Activating Token Index: 327

Text #18

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.1211. Min Act: -0.0000

Data Index: 550765 (The Pile)

Max Activating Token Index: 620

Text #19

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.0693. Min Act: -0.0000

Data Index: 180507 (The Pile)

Max Activating Token Index: 832