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

Dataset: The Pile

Neuron 1144 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1593. Min Range: -1.1593

Max Act: 1.1593. Min Act: -0.0000

Data Index: 641310 (The Pile)

Max Activating Token Index: 887

Text #1

Max Range: 1.1593. Min Range: -1.1593

Max Act: 1.1380. Min Act: -0.0000

Data Index: 1150032 (The Pile)

Max Activating Token Index: 50

Text #2

Max Range: 1.1593. Min Range: -1.1593

Max Act: 1.1329. Min Act: -0.0000

Data Index: 683341 (The Pile)

Max Activating Token Index: 575

Text #3

Max Range: 1.1593. Min Range: -1.1593

Max Act: 1.0646. Min Act: -0.0000

Data Index: 1345528 (The Pile)

Max Activating Token Index: 105

Text #4

Max Range: 1.1593. Min Range: -1.1593

Max Act: 1.0423. Min Act: -0.0000

Data Index: 1476434 (The Pile)

Max Activating Token Index: 388

Text #5

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.9807. Min Act: -0.0000

Data Index: 1601358 (The Pile)

Max Activating Token Index: 319

Text #6

Max Range: 1.1593. Min Range: -1.1593

Max Act: 1.0043. Min Act: -0.0000

Data Index: 1858395 (The Pile)

Max Activating Token Index: 920

Text #7

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.9984. Min Act: -0.0000

Data Index: 1049789 (The Pile)

Max Activating Token Index: 103

Text #8

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.9434. Min Act: -0.0000

Data Index: 1702593 (The Pile)

Max Activating Token Index: 973

Text #9

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.9803. Min Act: -0.0000

Data Index: 273780 (The Pile)

Max Activating Token Index: 810

Text #10

Max Range: 1.1593. Min Range: -1.1593

Max Act: 1.0419. Min Act: -0.0000

Data Index: 625788 (The Pile)

Max Activating Token Index: 723

Text #11

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.9736. Min Act: -0.0000

Data Index: 1414791 (The Pile)

Max Activating Token Index: 409

Text #12

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.9645. Min Act: -0.0000

Data Index: 1039460 (The Pile)

Max Activating Token Index: 665

Text #13

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.9949. Min Act: -0.0000

Data Index: 1502404 (The Pile)

Max Activating Token Index: 49

Text #14

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.8799. Min Act: -0.0000

Data Index: 91227 (The Pile)

Max Activating Token Index: 889

Text #15

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.9139. Min Act: -0.0000

Data Index: 950393 (The Pile)

Max Activating Token Index: 597

Text #16

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.9603. Min Act: -0.0000

Data Index: 1262647 (The Pile)

Max Activating Token Index: 356

Text #17

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.8472. Min Act: -0.0000

Data Index: 51766 (The Pile)

Max Activating Token Index: 327

Text #18

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.8936. Min Act: -0.0000

Data Index: 594010 (The Pile)

Max Activating Token Index: 374

Text #19

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.8425. Min Act: -0.0000

Data Index: 1097966 (The Pile)

Max Activating Token Index: 307