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

Dataset: The Pile

Neuron 2646 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.7701. Min Act: -0.0001

Data Index: 1913823 (The Pile)

Max Activating Token Index: 61

Text #1

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.7686. Min Act: -0.0000

Data Index: 1414526 (The Pile)

Max Activating Token Index: 63

Text #2

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.6991. Min Act: -0.0000

Data Index: 101717 (The Pile)

Max Activating Token Index: 208

Text #3

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.7256. Min Act: -0.0001

Data Index: 634328 (The Pile)

Max Activating Token Index: 236

Text #4

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.6775. Min Act: -0.0001

Data Index: 1610533 (The Pile)

Max Activating Token Index: 300

Text #5

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.7358. Min Act: -0.0000

Data Index: 360882 (The Pile)

Max Activating Token Index: 220

Text #6

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.6830. Min Act: -0.0001

Data Index: 1242428 (The Pile)

Max Activating Token Index: 37

Text #7

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.6626. Min Act: -0.0000

Data Index: 1403192 (The Pile)

Max Activating Token Index: 326

Text #8

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.6564. Min Act: -0.0000

Data Index: 1692691 (The Pile)

Max Activating Token Index: 137

Text #9

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.6571. Min Act: -0.0000

Data Index: 1983989 (The Pile)

Max Activating Token Index: 206

Text #10

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.7093. Min Act: -0.0000

Data Index: 124042 (The Pile)

Max Activating Token Index: 4

Text #11

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.6591. Min Act: -0.0000

Data Index: 40769 (The Pile)

Max Activating Token Index: 901

Text #12

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.6735. Min Act: -0.0000

Data Index: 1659344 (The Pile)

Max Activating Token Index: 623

Text #13

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.6709. Min Act: -0.0000

Data Index: 1461131 (The Pile)

Max Activating Token Index: 434

Text #14

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.6471. Min Act: -0.0001

Data Index: 1563077 (The Pile)

Max Activating Token Index: 710

Text #15

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.7122. Min Act: -0.0001

Data Index: 1305861 (The Pile)

Max Activating Token Index: 918

Text #16

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.6194. Min Act: -0.0000

Data Index: 1554134 (The Pile)

Max Activating Token Index: 43

Text #17

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.6683. Min Act: -0.0000

Data Index: 49203 (The Pile)

Max Activating Token Index: 4

Text #18

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.6422. Min Act: -0.0000

Data Index: 313574 (The Pile)

Max Activating Token Index: 551

Text #19

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.6634. Min Act: -0.0000

Data Index: 238335 (The Pile)

Max Activating Token Index: 596