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

Dataset: The Pile

Neuron 3066 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: 0.9526. Min Range: -0.9526

Max Act: 0.9526. Min Act: -0.0000

Data Index: 427048 (The Pile)

Max Activating Token Index: 737

Text #1

Max Range: 0.9526. Min Range: -0.9526

Max Act: 0.7430. Min Act: -0.0000

Data Index: 1950407 (The Pile)

Max Activating Token Index: 159

Text #2

Max Range: 0.9526. Min Range: -0.9526

Max Act: 0.7688. Min Act: -0.0000

Data Index: 653423 (The Pile)

Max Activating Token Index: 758

Text #3

Max Range: 0.9526. Min Range: -0.9526

Max Act: 0.7536. Min Act: -0.0000

Data Index: 1410568 (The Pile)

Max Activating Token Index: 1010

Text #4

Max Range: 0.9526. Min Range: -0.9526

Max Act: 0.7417. Min Act: -0.0000

Data Index: 1773432 (The Pile)

Max Activating Token Index: 333

Text #5

Max Range: 0.9526. Min Range: -0.9526

Max Act: 0.7335. Min Act: -0.0000

Data Index: 729003 (The Pile)

Max Activating Token Index: 379

Text #6

Max Range: 0.9526. Min Range: -0.9526

Max Act: 0.7277. Min Act: -0.0000

Data Index: 1196114 (The Pile)

Max Activating Token Index: 992

Text #7

Max Range: 0.9526. Min Range: -0.9526

Max Act: 0.6593. Min Act: -0.0000

Data Index: 1272327 (The Pile)

Max Activating Token Index: 133

Text #8

Max Range: 0.9526. Min Range: -0.9526

Max Act: 0.6535. Min Act: -0.0000

Data Index: 926289 (The Pile)

Max Activating Token Index: 294

Text #9

Max Range: 0.9526. Min Range: -0.9526

Max Act: 0.6405. Min Act: -0.0000

Data Index: 536344 (The Pile)

Max Activating Token Index: 708

Text #10

Max Range: 0.9526. Min Range: -0.9526

Max Act: 0.6519. Min Act: -0.0000

Data Index: 1314364 (The Pile)

Max Activating Token Index: 920

Text #11

Max Range: 0.9526. Min Range: -0.9526

Max Act: 0.6016. Min Act: -0.0000

Data Index: 904886 (The Pile)

Max Activating Token Index: 220

Text #12

Max Range: 0.9526. Min Range: -0.9526

Max Act: 0.6346. Min Act: -0.0000

Data Index: 1430593 (The Pile)

Max Activating Token Index: 530

Text #13

Max Range: 0.9526. Min Range: -0.9526

Max Act: 0.5771. Min Act: -0.0000

Data Index: 750505 (The Pile)

Max Activating Token Index: 765

Text #14

Max Range: 0.9526. Min Range: -0.9526

Max Act: 0.5786. Min Act: -0.0000

Data Index: 1250833 (The Pile)

Max Activating Token Index: 1012

Text #15

Max Range: 0.9526. Min Range: -0.9526

Max Act: 0.5769. Min Act: -0.0000

Data Index: 1426358 (The Pile)

Max Activating Token Index: 554

Text #16

Max Range: 0.9526. Min Range: -0.9526

Max Act: 0.6329. Min Act: -0.0000

Data Index: 1286635 (The Pile)

Max Activating Token Index: 515

Text #17

Max Range: 0.9526. Min Range: -0.9526

Max Act: 0.5940. Min Act: -0.0000

Data Index: 1409234 (The Pile)

Max Activating Token Index: 594

Text #18

Max Range: 0.9526. Min Range: -0.9526

Max Act: 0.5719. Min Act: -0.0000

Data Index: 1205561 (The Pile)

Max Activating Token Index: 831

Text #19

Max Range: 0.9526. Min Range: -0.9526

Max Act: 0.6042. Min Act: -0.0000

Data Index: 560515 (The Pile)

Max Activating Token Index: 657