Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2876 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.5730. Min Act: -0.0000

Data Index: 1851454 (The Pile)

Max Activating Token Index: 646

Text #1

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.5337. Min Act: -0.0000

Data Index: 1274285 (The Pile)

Max Activating Token Index: 455

Text #2

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.5282. Min Act: -0.0000

Data Index: 596508 (The Pile)

Max Activating Token Index: 377

Text #3

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.5076. Min Act: -0.0000

Data Index: 1487531 (The Pile)

Max Activating Token Index: 981

Text #4

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4419. Min Act: -0.0000

Data Index: 1349920 (The Pile)

Max Activating Token Index: 420

Text #5

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4474. Min Act: -0.0000

Data Index: 1515971 (The Pile)

Max Activating Token Index: 539

Text #6

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4566. Min Act: -0.0000

Data Index: 488389 (The Pile)

Max Activating Token Index: 491

Text #7

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4414. Min Act: -0.0000

Data Index: 707067 (The Pile)

Max Activating Token Index: 835

Text #8

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4497. Min Act: -0.0000

Data Index: 1691822 (The Pile)

Max Activating Token Index: 120

Text #9

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4504. Min Act: -0.0000

Data Index: 912957 (The Pile)

Max Activating Token Index: 198

Text #10

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4268. Min Act: -0.0000

Data Index: 476118 (The Pile)

Max Activating Token Index: 181

Text #11

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4226. Min Act: -0.0000

Data Index: 1715775 (The Pile)

Max Activating Token Index: 788

Text #12

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4116. Min Act: -0.0000

Data Index: 1451549 (The Pile)

Max Activating Token Index: 982

Text #13

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4174. Min Act: -0.0000

Data Index: 1393860 (The Pile)

Max Activating Token Index: 806

Text #14

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.3855. Min Act: -0.0000

Data Index: 1347802 (The Pile)

Max Activating Token Index: 616

Text #15

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4009. Min Act: -0.0000

Data Index: 1256410 (The Pile)

Max Activating Token Index: 86

Text #16

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4072. Min Act: -0.0000

Data Index: 687458 (The Pile)

Max Activating Token Index: 257

Text #17

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4036. Min Act: -0.0000

Data Index: 706869 (The Pile)

Max Activating Token Index: 738

Text #18

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.3804. Min Act: -0.0000

Data Index: 1631366 (The Pile)

Max Activating Token Index: 569

Text #19

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.3541. Min Act: -0.0000

Data Index: 1054353 (The Pile)

Max Activating Token Index: 56