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

Dataset: The Pile

Neuron 1928 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: 0.7915. Min Range: -0.7915

Max Act: 0.7915. Min Act: -0.0000

Data Index: 544976 (The Pile)

Max Activating Token Index: 320

Text #1

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.7304. Min Act: -0.0000

Data Index: 1536860 (The Pile)

Max Activating Token Index: 848

Text #2

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.7348. Min Act: -0.0000

Data Index: 1744466 (The Pile)

Max Activating Token Index: 199

Text #3

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.7806. Min Act: -0.0000

Data Index: 1340284 (The Pile)

Max Activating Token Index: 740

Text #4

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.7777. Min Act: -0.0000

Data Index: 1621417 (The Pile)

Max Activating Token Index: 433

Text #5

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.7326. Min Act: -0.0000

Data Index: 337683 (The Pile)

Max Activating Token Index: 586

Text #6

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.7531. Min Act: -0.0000

Data Index: 526220 (The Pile)

Max Activating Token Index: 791

Text #7

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.7289. Min Act: -0.0000

Data Index: 298286 (The Pile)

Max Activating Token Index: 797

Text #8

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.7230. Min Act: -0.0000

Data Index: 1951950 (The Pile)

Max Activating Token Index: 468

Text #9

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.7481. Min Act: -0.0000

Data Index: 768645 (The Pile)

Max Activating Token Index: 684

Text #10

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.6966. Min Act: -0.0000

Data Index: 153472 (The Pile)

Max Activating Token Index: 906

Text #11

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.6878. Min Act: -0.0000

Data Index: 377108 (The Pile)

Max Activating Token Index: 506

Text #12

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.7152. Min Act: -0.0000

Data Index: 1082560 (The Pile)

Max Activating Token Index: 372

Text #13

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.6870. Min Act: -0.0000

Data Index: 692331 (The Pile)

Max Activating Token Index: 157

Text #14

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.6643. Min Act: -0.0000

Data Index: 935130 (The Pile)

Max Activating Token Index: 618

Text #15

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.7033. Min Act: -0.0000

Data Index: 1088577 (The Pile)

Max Activating Token Index: 121

Text #16

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.6868. Min Act: -0.0000

Data Index: 1068473 (The Pile)

Max Activating Token Index: 660

Text #17

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.6815. Min Act: -0.0000

Data Index: 1651919 (The Pile)

Max Activating Token Index: 481

Text #18

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.6769. Min Act: -0.0000

Data Index: 719586 (The Pile)

Max Activating Token Index: 137

Text #19

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.6558. Min Act: -0.0000

Data Index: 1464329 (The Pile)

Max Activating Token Index: 1011