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

Dataset: The Pile

Neuron 2753 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.9770. Min Range: -3.9770

Max Act: 3.9770. Min Act: -0.0000

Data Index: 1392427 (The Pile)

Max Activating Token Index: 878

Text #1

Max Range: 3.9770. Min Range: -3.9770

Max Act: 3.5980. Min Act: -0.0000

Data Index: 654488 (The Pile)

Max Activating Token Index: 136

Text #2

Max Range: 3.9770. Min Range: -3.9770

Max Act: 3.7483. Min Act: -0.0000

Data Index: 1682582 (The Pile)

Max Activating Token Index: 268

Text #3

Max Range: 3.9770. Min Range: -3.9770

Max Act: 3.7999. Min Act: -0.0000

Data Index: 45262 (The Pile)

Max Activating Token Index: 921

Text #4

Max Range: 3.9770. Min Range: -3.9770

Max Act: 3.3960. Min Act: -0.0000

Data Index: 1213336 (The Pile)

Max Activating Token Index: 598

Text #5

Max Range: 3.9770. Min Range: -3.9770

Max Act: 3.1378. Min Act: -0.0000

Data Index: 8101 (The Pile)

Max Activating Token Index: 426

Text #6

Max Range: 3.9770. Min Range: -3.9770

Max Act: 3.3543. Min Act: -0.0000

Data Index: 825551 (The Pile)

Max Activating Token Index: 121

Text #7

Max Range: 3.9770. Min Range: -3.9770

Max Act: 3.4491. Min Act: -0.0000

Data Index: 523264 (The Pile)

Max Activating Token Index: 651

Text #8

Max Range: 3.9770. Min Range: -3.9770

Max Act: 3.0740. Min Act: -0.0000

Data Index: 1530713 (The Pile)

Max Activating Token Index: 575

Text #9

Max Range: 3.9770. Min Range: -3.9770

Max Act: 3.2955. Min Act: -0.0000

Data Index: 1720546 (The Pile)

Max Activating Token Index: 742

Text #10

Max Range: 3.9770. Min Range: -3.9770

Max Act: 3.1840. Min Act: -0.0000

Data Index: 1555531 (The Pile)

Max Activating Token Index: 57

Text #11

Max Range: 3.9770. Min Range: -3.9770

Max Act: 2.9992. Min Act: -0.0000

Data Index: 1345067 (The Pile)

Max Activating Token Index: 433

Text #12

Max Range: 3.9770. Min Range: -3.9770

Max Act: 3.2834. Min Act: -0.0000

Data Index: 869539 (The Pile)

Max Activating Token Index: 81

Text #13

Max Range: 3.9770. Min Range: -3.9770

Max Act: 3.2475. Min Act: -0.0000

Data Index: 1371470 (The Pile)

Max Activating Token Index: 783

Text #14

Max Range: 3.9770. Min Range: -3.9770

Max Act: 3.0731. Min Act: -0.0000

Data Index: 382100 (The Pile)

Max Activating Token Index: 750

Text #15

Max Range: 3.9770. Min Range: -3.9770

Max Act: 3.0343. Min Act: -0.0000

Data Index: 881527 (The Pile)

Max Activating Token Index: 131

Text #16

Max Range: 3.9770. Min Range: -3.9770

Max Act: 3.0131. Min Act: -0.0000

Data Index: 322528 (The Pile)

Max Activating Token Index: 337

Text #17

Max Range: 3.9770. Min Range: -3.9770

Max Act: 2.8713. Min Act: -0.0000

Data Index: 1607453 (The Pile)

Max Activating Token Index: 479

Text #18

Max Range: 3.9770. Min Range: -3.9770

Max Act: 2.8056. Min Act: -0.0000

Data Index: 1980216 (The Pile)

Max Activating Token Index: 854

Text #19

Max Range: 3.9770. Min Range: -3.9770

Max Act: 2.8916. Min Act: 0.0000

Data Index: 242978 (The Pile)

Max Activating Token Index: 60