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

Dataset: The Pile

Neuron 1449 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: 0.3767. Min Range: -0.3767

Max Act: 0.3767. Min Act: -0.0000

Data Index: 209865 (The Pile)

Max Activating Token Index: 65

Text #1

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3620. Min Act: -0.0000

Data Index: 1882371 (The Pile)

Max Activating Token Index: 1013

Text #2

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3637. Min Act: -0.0000

Data Index: 922581 (The Pile)

Max Activating Token Index: 328

Text #3

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3270. Min Act: -0.0000

Data Index: 1237005 (The Pile)

Max Activating Token Index: 122

Text #4

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3070. Min Act: -0.0000

Data Index: 1207889 (The Pile)

Max Activating Token Index: 824

Text #5

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2701. Min Act: -0.0000

Data Index: 347562 (The Pile)

Max Activating Token Index: 521

Text #6

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3393. Min Act: -0.0000

Data Index: 19600 (The Pile)

Max Activating Token Index: 666

Text #7

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2913. Min Act: -0.0000

Data Index: 327380 (The Pile)

Max Activating Token Index: 837

Text #8

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2906. Min Act: -0.0000

Data Index: 591445 (The Pile)

Max Activating Token Index: 588

Text #9

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2544. Min Act: -0.0000

Data Index: 1854737 (The Pile)

Max Activating Token Index: 39

Text #10

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2801. Min Act: -0.0000

Data Index: 737687 (The Pile)

Max Activating Token Index: 504

Text #11

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2509. Min Act: -0.0000

Data Index: 1255646 (The Pile)

Max Activating Token Index: 94

Text #12

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2362. Min Act: -0.0000

Data Index: 597239 (The Pile)

Max Activating Token Index: 449

Text #13

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2350. Min Act: -0.0000

Data Index: 63936 (The Pile)

Max Activating Token Index: 974

Text #14

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2782. Min Act: -0.0000

Data Index: 285477 (The Pile)

Max Activating Token Index: 884

Text #15

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2903. Min Act: -0.0000

Data Index: 1975300 (The Pile)

Max Activating Token Index: 522

Text #16

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2649. Min Act: -0.0000

Data Index: 950681 (The Pile)

Max Activating Token Index: 270

Text #17

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2684. Min Act: -0.0000

Data Index: 761005 (The Pile)

Max Activating Token Index: 406

Text #18

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2704. Min Act: -0.0000

Data Index: 740481 (The Pile)

Max Activating Token Index: 876

Text #19

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2352. Min Act: -0.0000

Data Index: 473925 (The Pile)

Max Activating Token Index: 872