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

Dataset: The Pile

Neuron 4110 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: 4.0030. Min Range: -4.0030

Max Act: 4.0030. Min Act: -0.0000

Data Index: 1506478 (The Pile)

Max Activating Token Index: 737

Text #1

Max Range: 4.0030. Min Range: -4.0030

Max Act: 3.4305. Min Act: -0.0000

Data Index: 1403101 (The Pile)

Max Activating Token Index: 239

Text #2

Max Range: 4.0030. Min Range: -4.0030

Max Act: 3.9355. Min Act: -0.0000

Data Index: 1299273 (The Pile)

Max Activating Token Index: 729

Text #3

Max Range: 4.0030. Min Range: -4.0030

Max Act: 3.4827. Min Act: -0.0000

Data Index: 1261702 (The Pile)

Max Activating Token Index: 610

Text #4

Max Range: 4.0030. Min Range: -4.0030

Max Act: 3.3929. Min Act: -0.0000

Data Index: 1195293 (The Pile)

Max Activating Token Index: 750

Text #5

Max Range: 4.0030. Min Range: -4.0030

Max Act: 3.4231. Min Act: -0.0000

Data Index: 376033 (The Pile)

Max Activating Token Index: 437

Text #6

Max Range: 4.0030. Min Range: -4.0030

Max Act: 3.4688. Min Act: -0.0000

Data Index: 1269079 (The Pile)

Max Activating Token Index: 751

Text #7

Max Range: 4.0030. Min Range: -4.0030

Max Act: 3.6273. Min Act: -0.0000

Data Index: 365988 (The Pile)

Max Activating Token Index: 814

Text #8

Max Range: 4.0030. Min Range: -4.0030

Max Act: 3.6639. Min Act: -0.0000

Data Index: 1747860 (The Pile)

Max Activating Token Index: 741

Text #9

Max Range: 4.0030. Min Range: -4.0030

Max Act: 3.2537. Min Act: -0.0000

Data Index: 370798 (The Pile)

Max Activating Token Index: 839

Text #10

Max Range: 4.0030. Min Range: -4.0030

Max Act: 3.1056. Min Act: -0.0000

Data Index: 1774471 (The Pile)

Max Activating Token Index: 329

Text #11

Max Range: 4.0030. Min Range: -4.0030

Max Act: 3.4380. Min Act: -0.0000

Data Index: 92081 (The Pile)

Max Activating Token Index: 162

Text #12

Max Range: 4.0030. Min Range: -4.0030

Max Act: 3.5497. Min Act: -0.0000

Data Index: 167941 (The Pile)

Max Activating Token Index: 985

Text #13

Max Range: 4.0030. Min Range: -4.0030

Max Act: 3.1812. Min Act: -0.0000

Data Index: 1564949 (The Pile)

Max Activating Token Index: 853

Text #14

Max Range: 4.0030. Min Range: -4.0030

Max Act: 2.7215. Min Act: -0.0000

Data Index: 1385308 (The Pile)

Max Activating Token Index: 695

Text #15

Max Range: 4.0030. Min Range: -4.0030

Max Act: 2.3547. Min Act: -0.0000

Data Index: 1745814 (The Pile)

Max Activating Token Index: 925

Text #16

Max Range: 4.0030. Min Range: -4.0030

Max Act: 2.9415. Min Act: -0.0000

Data Index: 591222 (The Pile)

Max Activating Token Index: 713

Text #17

Max Range: 4.0030. Min Range: -4.0030

Max Act: 2.8043. Min Act: -0.0000

Data Index: 1095584 (The Pile)

Max Activating Token Index: 858

Text #18

Max Range: 4.0030. Min Range: -4.0030

Max Act: 2.7784. Min Act: -0.0000

Data Index: 104420 (The Pile)

Max Activating Token Index: 784

Text #19

Max Range: 4.0030. Min Range: -4.0030

Max Act: 2.7500. Min Act: -0.0000

Data Index: 71019 (The Pile)

Max Activating Token Index: 448