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

Dataset: The Pile

Neuron 2775 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: 0.6688. Min Range: -0.6688

Max Act: 0.6658. Min Act: -0.0000

Data Index: 512411 (The Pile)

Max Activating Token Index: 727

Text #1

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.6400. Min Act: -0.0000

Data Index: 1527858 (The Pile)

Max Activating Token Index: 591

Text #2

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.5960. Min Act: -0.0000

Data Index: 1769977 (The Pile)

Max Activating Token Index: 65

Text #3

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.5844. Min Act: -0.0000

Data Index: 200607 (The Pile)

Max Activating Token Index: 775

Text #4

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.6688. Min Act: -0.0000

Data Index: 778341 (The Pile)

Max Activating Token Index: 870

Text #5

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.5844. Min Act: -0.0000

Data Index: 845697 (The Pile)

Max Activating Token Index: 893

Text #6

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.6249. Min Act: -0.0000

Data Index: 1872701 (The Pile)

Max Activating Token Index: 1018

Text #7

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.5792. Min Act: -0.0000

Data Index: 1838943 (The Pile)

Max Activating Token Index: 947

Text #8

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.5800. Min Act: -0.0000

Data Index: 784383 (The Pile)

Max Activating Token Index: 719

Text #9

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.5668. Min Act: -0.0000

Data Index: 1533664 (The Pile)

Max Activating Token Index: 1018

Text #10

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.5362. Min Act: -0.0000

Data Index: 1914828 (The Pile)

Max Activating Token Index: 102

Text #11

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.5296. Min Act: -0.0000

Data Index: 1514246 (The Pile)

Max Activating Token Index: 930

Text #12

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.6038. Min Act: -0.0000

Data Index: 1695554 (The Pile)

Max Activating Token Index: 997

Text #13

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.5166. Min Act: -0.0000

Data Index: 1145708 (The Pile)

Max Activating Token Index: 985

Text #14

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.5604. Min Act: -0.0000

Data Index: 24301 (The Pile)

Max Activating Token Index: 719

Text #15

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.5397. Min Act: -0.0000

Data Index: 440682 (The Pile)

Max Activating Token Index: 902

Text #16

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.5145. Min Act: -0.0000

Data Index: 750152 (The Pile)

Max Activating Token Index: 341

Text #17

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.5095. Min Act: -0.0000

Data Index: 1002604 (The Pile)

Max Activating Token Index: 382

Text #18

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.5281. Min Act: -0.0000

Data Index: 1352446 (The Pile)

Max Activating Token Index: 671

Text #19

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.5263. Min Act: -0.0000

Data Index: 1182934 (The Pile)

Max Activating Token Index: 100