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

Dataset: The Pile

Neuron 4241 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.4112. Min Act: -0.0000

Data Index: 278924 (The Pile)

Max Activating Token Index: 327

Text #1

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.3071. Min Act: -0.0000

Data Index: 1914959 (The Pile)

Max Activating Token Index: 483

Text #2

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.4700. Min Act: -0.0000

Data Index: 1196824 (The Pile)

Max Activating Token Index: 175

Text #3

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.3197. Min Act: -0.0000

Data Index: 1801809 (The Pile)

Max Activating Token Index: 428

Text #4

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.1514. Min Act: -0.0000

Data Index: 719859 (The Pile)

Max Activating Token Index: 17

Text #5

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.2118. Min Act: -0.0000

Data Index: 878714 (The Pile)

Max Activating Token Index: 468

Text #6

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.1899. Min Act: -0.0000

Data Index: 696753 (The Pile)

Max Activating Token Index: 83

Text #7

Max Range: 1.4700. Min Range: -1.4700

Max Act: 0.9000. Min Act: -0.0000

Data Index: 185744 (The Pile)

Max Activating Token Index: 676

Text #8

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.2047. Min Act: -0.0000

Data Index: 1636363 (The Pile)

Max Activating Token Index: 297

Text #9

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.1090. Min Act: -0.0000

Data Index: 1201781 (The Pile)

Max Activating Token Index: 303

Text #10

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.2498. Min Act: -0.0000

Data Index: 1079614 (The Pile)

Max Activating Token Index: 272

Text #11

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.1300. Min Act: -0.0000

Data Index: 1262488 (The Pile)

Max Activating Token Index: 867

Text #12

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.2404. Min Act: -0.0000

Data Index: 1536993 (The Pile)

Max Activating Token Index: 663

Text #13

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.1082. Min Act: -0.0000

Data Index: 1186688 (The Pile)

Max Activating Token Index: 179

Text #14

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.1111. Min Act: -0.0000

Data Index: 39866 (The Pile)

Max Activating Token Index: 598

Text #15

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.0768. Min Act: -0.0000

Data Index: 873844 (The Pile)

Max Activating Token Index: 447

Text #16

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.1269. Min Act: -0.0000

Data Index: 1165037 (The Pile)

Max Activating Token Index: 795

Text #17

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.1457. Min Act: -0.0000

Data Index: 964852 (The Pile)

Max Activating Token Index: 510

Text #18

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.0794. Min Act: -0.0000

Data Index: 1004866 (The Pile)

Max Activating Token Index: 441

Text #19

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.0688. Min Act: -0.0000

Data Index: 1802445 (The Pile)

Max Activating Token Index: 383