Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3387 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.9033. Min Act: -0.0000

Data Index: 505267 (The Pile)

Max Activating Token Index: 108

Text #1

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.8575. Min Act: 0.0000

Data Index: 11833 (The Pile)

Max Activating Token Index: 587

Text #2

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.6618. Min Act: -0.0000

Data Index: 146048 (The Pile)

Max Activating Token Index: 393

Text #3

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.6321. Min Act: -0.0000

Data Index: 151856 (The Pile)

Max Activating Token Index: 472

Text #4

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.6390. Min Act: 0.0000

Data Index: 1052782 (The Pile)

Max Activating Token Index: 646

Text #5

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.5803. Min Act: -0.0000

Data Index: 1789277 (The Pile)

Max Activating Token Index: 747

Text #6

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.6139. Min Act: -0.0000

Data Index: 1901416 (The Pile)

Max Activating Token Index: 833

Text #7

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.6041. Min Act: -0.0000

Data Index: 1064217 (The Pile)

Max Activating Token Index: 937

Text #8

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.6047. Min Act: -0.0000

Data Index: 1856712 (The Pile)

Max Activating Token Index: 586

Text #9

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.6514. Min Act: -0.0000

Data Index: 928945 (The Pile)

Max Activating Token Index: 681

Text #10

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.5719. Min Act: -0.0000

Data Index: 94040 (The Pile)

Max Activating Token Index: 489

Text #11

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.5765. Min Act: -0.0000

Data Index: 143717 (The Pile)

Max Activating Token Index: 148

Text #12

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.5880. Min Act: -0.0000

Data Index: 882008 (The Pile)

Max Activating Token Index: 750

Text #13

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.5567. Min Act: -0.0000

Data Index: 972587 (The Pile)

Max Activating Token Index: 424

Text #14

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.5868. Min Act: -0.0000

Data Index: 1382728 (The Pile)

Max Activating Token Index: 522

Text #15

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.5086. Min Act: -0.0000

Data Index: 352273 (The Pile)

Max Activating Token Index: 549

Text #16

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.5404. Min Act: -0.0000

Data Index: 711097 (The Pile)

Max Activating Token Index: 155

Text #17

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.5203. Min Act: -0.0000

Data Index: 1637734 (The Pile)

Max Activating Token Index: 886

Text #18

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.5169. Min Act: -0.0000

Data Index: 1828592 (The Pile)

Max Activating Token Index: 253

Text #19

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.5334. Min Act: -0.0000

Data Index: 1738965 (The Pile)

Max Activating Token Index: 488