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

Dataset: The Pile

Neuron 3662 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.5810. Min Act: -0.0000

Data Index: 885528 (The Pile)

Max Activating Token Index: 137

Text #1

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.5786. Min Act: -0.0000

Data Index: 1677139 (The Pile)

Max Activating Token Index: 372

Text #2

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4329. Min Act: -0.0000

Data Index: 375654 (The Pile)

Max Activating Token Index: 656

Text #3

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4388. Min Act: -0.0000

Data Index: 1073998 (The Pile)

Max Activating Token Index: 207

Text #4

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4581. Min Act: -0.0000

Data Index: 1230179 (The Pile)

Max Activating Token Index: 984

Text #5

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4348. Min Act: -0.0000

Data Index: 23222 (The Pile)

Max Activating Token Index: 256

Text #6

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4042. Min Act: -0.0000

Data Index: 1566443 (The Pile)

Max Activating Token Index: 654

Text #7

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.3944. Min Act: -0.0000

Data Index: 1084693 (The Pile)

Max Activating Token Index: 576

Text #8

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4154. Min Act: -0.0000

Data Index: 478525 (The Pile)

Max Activating Token Index: 70

Text #9

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.3745. Min Act: -0.0000

Data Index: 1758180 (The Pile)

Max Activating Token Index: 242

Text #10

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.3541. Min Act: -0.0000

Data Index: 1681277 (The Pile)

Max Activating Token Index: 799

Text #11

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.3956. Min Act: -0.0000

Data Index: 1251953 (The Pile)

Max Activating Token Index: 361

Text #12

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.3938. Min Act: -0.0000

Data Index: 539115 (The Pile)

Max Activating Token Index: 21

Text #13

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.3748. Min Act: -0.0000

Data Index: 136565 (The Pile)

Max Activating Token Index: 852

Text #14

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.3895. Min Act: -0.0000

Data Index: 1068128 (The Pile)

Max Activating Token Index: 118

Text #15

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.3469. Min Act: 0.0000

Data Index: 1020027 (The Pile)

Max Activating Token Index: 70

Text #16

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.3854. Min Act: -0.0000

Data Index: 1740673 (The Pile)

Max Activating Token Index: 609

Text #17

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.3471. Min Act: -0.0000

Data Index: 1462854 (The Pile)

Max Activating Token Index: 688

Text #18

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.3477. Min Act: -0.0000

Data Index: 1863924 (The Pile)

Max Activating Token Index: 816

Text #19

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.3641. Min Act: 0.0000

Data Index: 1880548 (The Pile)

Max Activating Token Index: 43