Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2501 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1024. Min Act: -0.0001

Data Index: 1709914 (The Pile)

Max Activating Token Index: 917

Text #1

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0827. Min Act: -0.0000

Data Index: 1550068 (The Pile)

Max Activating Token Index: 821

Text #2

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0789. Min Act: -0.0000

Data Index: 1695684 (The Pile)

Max Activating Token Index: 647

Text #3

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0782. Min Act: -0.0000

Data Index: 1901735 (The Pile)

Max Activating Token Index: 879

Text #4

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0802. Min Act: -0.0000

Data Index: 1991238 (The Pile)

Max Activating Token Index: 837

Text #5

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0769. Min Act: -0.0000

Data Index: 426842 (The Pile)

Max Activating Token Index: 217

Text #6

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0764. Min Act: -0.0000

Data Index: 1109901 (The Pile)

Max Activating Token Index: 649

Text #7

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0777. Min Act: -0.0000

Data Index: 319571 (The Pile)

Max Activating Token Index: 895

Text #8

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0714. Min Act: -0.0000

Data Index: 230904 (The Pile)

Max Activating Token Index: 938

Text #9

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0742. Min Act: -0.0000

Data Index: 845474 (The Pile)

Max Activating Token Index: 845

Text #10

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0759. Min Act: -0.0000

Data Index: 44220 (The Pile)

Max Activating Token Index: 528

Text #11

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0692. Min Act: -0.0001

Data Index: 140246 (The Pile)

Max Activating Token Index: 899

Text #12

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0735. Min Act: -0.0000

Data Index: 254036 (The Pile)

Max Activating Token Index: 877

Text #13

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0698. Min Act: -0.0000

Data Index: 822308 (The Pile)

Max Activating Token Index: 669

Text #14

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0677. Min Act: -0.0000

Data Index: 1094248 (The Pile)

Max Activating Token Index: 840

Text #15

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0742. Min Act: -0.0000

Data Index: 725898 (The Pile)

Max Activating Token Index: 274

Text #16

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0747. Min Act: -0.0000

Data Index: 204053 (The Pile)

Max Activating Token Index: 966

Text #17

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0653. Min Act: 0.0001

Data Index: 531467 (The Pile)

Max Activating Token Index: 93

Text #18

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0657. Min Act: -0.0000

Data Index: 972526 (The Pile)

Max Activating Token Index: 614

Text #19

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0668. Min Act: -0.0001

Data Index: 659614 (The Pile)

Max Activating Token Index: 510