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

Dataset: The Pile

Neuron 4919 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: 1.4371. Min Range: -1.4371

Max Act: 1.4371. Min Act: -0.0000

Data Index: 312479 (The Pile)

Max Activating Token Index: 649

Text #1

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.3017. Min Act: -0.0000

Data Index: 1185458 (The Pile)

Max Activating Token Index: 741

Text #2

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.2552. Min Act: -0.0000

Data Index: 1589003 (The Pile)

Max Activating Token Index: 603

Text #3

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.2744. Min Act: -0.0000

Data Index: 1985222 (The Pile)

Max Activating Token Index: 80

Text #4

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.2364. Min Act: -0.0000

Data Index: 1065388 (The Pile)

Max Activating Token Index: 665

Text #5

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.2250. Min Act: -0.0000

Data Index: 930109 (The Pile)

Max Activating Token Index: 552

Text #6

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.2630. Min Act: -0.0000

Data Index: 1769800 (The Pile)

Max Activating Token Index: 113

Text #7

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.2123. Min Act: -0.0000

Data Index: 1760054 (The Pile)

Max Activating Token Index: 29

Text #8

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.2039. Min Act: -0.0000

Data Index: 339673 (The Pile)

Max Activating Token Index: 510

Text #9

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.1639. Min Act: -0.0000

Data Index: 116572 (The Pile)

Max Activating Token Index: 112

Text #10

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.2263. Min Act: -0.0000

Data Index: 1380387 (The Pile)

Max Activating Token Index: 578

Text #11

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.2330. Min Act: -0.0000

Data Index: 627255 (The Pile)

Max Activating Token Index: 1021

Text #12

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.1773. Min Act: -0.0000

Data Index: 324824 (The Pile)

Max Activating Token Index: 689

Text #13

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.1348. Min Act: -0.0000

Data Index: 1784489 (The Pile)

Max Activating Token Index: 583

Text #14

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.1993. Min Act: -0.0000

Data Index: 908977 (The Pile)

Max Activating Token Index: 173

Text #15

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.1894. Min Act: -0.0000

Data Index: 879697 (The Pile)

Max Activating Token Index: 431

Text #16

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.1850. Min Act: -0.0000

Data Index: 1628243 (The Pile)

Max Activating Token Index: 498

Text #17

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.1382. Min Act: -0.0000

Data Index: 255906 (The Pile)

Max Activating Token Index: 85

Text #18

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.1060. Min Act: -0.0000

Data Index: 939408 (The Pile)

Max Activating Token Index: 165

Text #19

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.1596. Min Act: -0.0000

Data Index: 1665786 (The Pile)

Max Activating Token Index: 1008