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

Dataset: The Pile

Neuron 932 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.6376. Min Act: -0.0000

Data Index: 804137 (The Pile)

Max Activating Token Index: 770

Text #1

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.6814. Min Act: -0.0000

Data Index: 1949673 (The Pile)

Max Activating Token Index: 898

Text #2

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.6561. Min Act: -0.0000

Data Index: 871267 (The Pile)

Max Activating Token Index: 841

Text #3

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5936. Min Act: -0.0000

Data Index: 182156 (The Pile)

Max Activating Token Index: 742

Text #4

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.6437. Min Act: -0.0000

Data Index: 41024 (The Pile)

Max Activating Token Index: 912

Text #5

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.6047. Min Act: -0.0000

Data Index: 557821 (The Pile)

Max Activating Token Index: 209

Text #6

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5942. Min Act: -0.0000

Data Index: 1799129 (The Pile)

Max Activating Token Index: 592

Text #7

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.6102. Min Act: -0.0000

Data Index: 1521508 (The Pile)

Max Activating Token Index: 726

Text #8

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.6083. Min Act: -0.0000

Data Index: 1064974 (The Pile)

Max Activating Token Index: 12

Text #9

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5887. Min Act: -0.0000

Data Index: 1427643 (The Pile)

Max Activating Token Index: 822

Text #10

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5803. Min Act: -0.0000

Data Index: 24407 (The Pile)

Max Activating Token Index: 216

Text #11

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.6109. Min Act: -0.0000

Data Index: 775905 (The Pile)

Max Activating Token Index: 654

Text #12

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.6582. Min Act: -0.0000

Data Index: 975592 (The Pile)

Max Activating Token Index: 639

Text #13

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.6341. Min Act: -0.0000

Data Index: 1919193 (The Pile)

Max Activating Token Index: 413

Text #14

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5999. Min Act: -0.0000

Data Index: 1276997 (The Pile)

Max Activating Token Index: 832

Text #15

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5901. Min Act: -0.0000

Data Index: 1939453 (The Pile)

Max Activating Token Index: 457

Text #16

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5878. Min Act: -0.0000

Data Index: 1315212 (The Pile)

Max Activating Token Index: 452

Text #17

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5675. Min Act: -0.0000

Data Index: 1161813 (The Pile)

Max Activating Token Index: 437

Text #18

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5656. Min Act: -0.0000

Data Index: 578671 (The Pile)

Max Activating Token Index: 496

Text #19

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5434. Min Act: -0.0000

Data Index: 284426 (The Pile)

Max Activating Token Index: 634