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

Dataset: The Pile

Neuron 771 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.4834. Min Act: -0.0000

Data Index: 325705 (The Pile)

Max Activating Token Index: 120

Text #1

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.5160. Min Act: -0.0000

Data Index: 143743 (The Pile)

Max Activating Token Index: 626

Text #2

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.5068. Min Act: -0.0000

Data Index: 1082243 (The Pile)

Max Activating Token Index: 573

Text #3

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.2410. Min Act: -0.0000

Data Index: 654047 (The Pile)

Max Activating Token Index: 773

Text #4

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.4122. Min Act: -0.0000

Data Index: 1452910 (The Pile)

Max Activating Token Index: 426

Text #5

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.4931. Min Act: -0.0000

Data Index: 651067 (The Pile)

Max Activating Token Index: 613

Text #6

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.3595. Min Act: -0.0000

Data Index: 1067028 (The Pile)

Max Activating Token Index: 607

Text #7

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.3866. Min Act: -0.0000

Data Index: 738046 (The Pile)

Max Activating Token Index: 760

Text #8

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.3710. Min Act: -0.0000

Data Index: 1263815 (The Pile)

Max Activating Token Index: 592

Text #9

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.4079. Min Act: -0.0000

Data Index: 398926 (The Pile)

Max Activating Token Index: 789

Text #10

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.3093. Min Act: -0.0000

Data Index: 442882 (The Pile)

Max Activating Token Index: 381

Text #11

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.4920. Min Act: -0.0000

Data Index: 1302850 (The Pile)

Max Activating Token Index: 733

Text #12

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.2636. Min Act: -0.0000

Data Index: 313488 (The Pile)

Max Activating Token Index: 884

Text #13

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.3182. Min Act: -0.0000

Data Index: 573186 (The Pile)

Max Activating Token Index: 484

Text #14

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.2991. Min Act: -0.0000

Data Index: 846619 (The Pile)

Max Activating Token Index: 899

Text #15

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.3969. Min Act: -0.0000

Data Index: 904931 (The Pile)

Max Activating Token Index: 196

Text #16

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.2511. Min Act: -0.0000

Data Index: 1153267 (The Pile)

Max Activating Token Index: 878

Text #17

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.4754. Min Act: -0.0000

Data Index: 1608331 (The Pile)

Max Activating Token Index: 903

Text #18

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.2799. Min Act: -0.0000

Data Index: 1337246 (The Pile)

Max Activating Token Index: 749

Text #19

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.0700. Min Act: -0.0000

Data Index: 1523940 (The Pile)

Max Activating Token Index: 610