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

Dataset: The Pile

Neuron 3595 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: 0.4460. Min Range: -0.4460

Max Act: 0.4460. Min Act: -0.0000

Data Index: 1442492 (The Pile)

Max Activating Token Index: 305

Text #1

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3820. Min Act: -0.0000

Data Index: 1668547 (The Pile)

Max Activating Token Index: 879

Text #2

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.4328. Min Act: -0.0000

Data Index: 492844 (The Pile)

Max Activating Token Index: 420

Text #3

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.4396. Min Act: -0.0000

Data Index: 900114 (The Pile)

Max Activating Token Index: 301

Text #4

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3824. Min Act: -0.0000

Data Index: 399797 (The Pile)

Max Activating Token Index: 965

Text #5

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3411. Min Act: -0.0000

Data Index: 45959 (The Pile)

Max Activating Token Index: 606

Text #6

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3641. Min Act: -0.0000

Data Index: 183501 (The Pile)

Max Activating Token Index: 773

Text #7

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3941. Min Act: -0.0000

Data Index: 709425 (The Pile)

Max Activating Token Index: 160

Text #8

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3716. Min Act: -0.0000

Data Index: 175353 (The Pile)

Max Activating Token Index: 94

Text #9

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3813. Min Act: -0.0000

Data Index: 1535108 (The Pile)

Max Activating Token Index: 609

Text #10

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3855. Min Act: -0.0000

Data Index: 787368 (The Pile)

Max Activating Token Index: 628

Text #11

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3637. Min Act: -0.0000

Data Index: 645882 (The Pile)

Max Activating Token Index: 152

Text #12

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3554. Min Act: -0.0000

Data Index: 360209 (The Pile)

Max Activating Token Index: 744

Text #13

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3513. Min Act: -0.0000

Data Index: 850942 (The Pile)

Max Activating Token Index: 547

Text #14

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3724. Min Act: -0.0000

Data Index: 340510 (The Pile)

Max Activating Token Index: 376

Text #15

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3886. Min Act: -0.0000

Data Index: 1394296 (The Pile)

Max Activating Token Index: 792

Text #16

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.4036. Min Act: -0.0000

Data Index: 1079883 (The Pile)

Max Activating Token Index: 969

Text #17

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.4186. Min Act: -0.0000

Data Index: 1876221 (The Pile)

Max Activating Token Index: 500

Text #18

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3573. Min Act: -0.0000

Data Index: 1643707 (The Pile)

Max Activating Token Index: 792

Text #19

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3889. Min Act: -0.0000

Data Index: 1955502 (The Pile)

Max Activating Token Index: 407