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

Dataset: The Pile

Neuron 610 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: 1.2841. Min Range: -1.2841

Max Act: 1.2841. Min Act: -0.0000

Data Index: 471071 (The Pile)

Max Activating Token Index: 504

Text #1

Max Range: 1.2841. Min Range: -1.2841

Max Act: 1.1302. Min Act: -0.0000

Data Index: 1230223 (The Pile)

Max Activating Token Index: 831

Text #2

Max Range: 1.2841. Min Range: -1.2841

Max Act: 1.1514. Min Act: -0.0000

Data Index: 66540 (The Pile)

Max Activating Token Index: 691

Text #3

Max Range: 1.2841. Min Range: -1.2841

Max Act: 1.0388. Min Act: -0.0000

Data Index: 1987353 (The Pile)

Max Activating Token Index: 706

Text #4

Max Range: 1.2841. Min Range: -1.2841

Max Act: 0.9233. Min Act: -0.0000

Data Index: 1625026 (The Pile)

Max Activating Token Index: 638

Text #5

Max Range: 1.2841. Min Range: -1.2841

Max Act: 0.9780. Min Act: -0.0000

Data Index: 1302739 (The Pile)

Max Activating Token Index: 86

Text #6

Max Range: 1.2841. Min Range: -1.2841

Max Act: 0.9771. Min Act: -0.0000

Data Index: 48310 (The Pile)

Max Activating Token Index: 769

Text #7

Max Range: 1.2841. Min Range: -1.2841

Max Act: 0.9152. Min Act: -0.0000

Data Index: 512251 (The Pile)

Max Activating Token Index: 322

Text #8

Max Range: 1.2841. Min Range: -1.2841

Max Act: 0.9580. Min Act: -0.0000

Data Index: 849749 (The Pile)

Max Activating Token Index: 928

Text #9

Max Range: 1.2841. Min Range: -1.2841

Max Act: 0.9014. Min Act: -0.0000

Data Index: 1247422 (The Pile)

Max Activating Token Index: 669

Text #10

Max Range: 1.2841. Min Range: -1.2841

Max Act: 0.9016. Min Act: -0.0000

Data Index: 1629921 (The Pile)

Max Activating Token Index: 656

Text #11

Max Range: 1.2841. Min Range: -1.2841

Max Act: 0.8905. Min Act: -0.0000

Data Index: 1529745 (The Pile)

Max Activating Token Index: 890

Text #12

Max Range: 1.2841. Min Range: -1.2841

Max Act: 0.8452. Min Act: -0.0000

Data Index: 1660584 (The Pile)

Max Activating Token Index: 941

Text #13

Max Range: 1.2841. Min Range: -1.2841

Max Act: 0.7761. Min Act: -0.0000

Data Index: 1403615 (The Pile)

Max Activating Token Index: 684

Text #14

Max Range: 1.2841. Min Range: -1.2841

Max Act: 0.8704. Min Act: -0.0000

Data Index: 658273 (The Pile)

Max Activating Token Index: 537

Text #15

Max Range: 1.2841. Min Range: -1.2841

Max Act: 0.8734. Min Act: -0.0000

Data Index: 757131 (The Pile)

Max Activating Token Index: 1003

Text #16

Max Range: 1.2841. Min Range: -1.2841

Max Act: 0.8861. Min Act: -0.0000

Data Index: 1972865 (The Pile)

Max Activating Token Index: 94

Text #17

Max Range: 1.2841. Min Range: -1.2841

Max Act: 0.8237. Min Act: -0.0000

Data Index: 1315275 (The Pile)

Max Activating Token Index: 480

Text #18

Max Range: 1.2841. Min Range: -1.2841

Max Act: 0.6971. Min Act: -0.0000

Data Index: 989992 (The Pile)

Max Activating Token Index: 974

Text #19

Max Range: 1.2841. Min Range: -1.2841

Max Act: 0.7981. Min Act: -0.0000

Data Index: 1006692 (The Pile)

Max Activating Token Index: 230