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

Dataset: The Pile

Neuron 111 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: 1.8758. Min Range: -1.8758

Max Act: 1.8326. Min Act: -0.0000

Data Index: 1951308 (The Pile)

Max Activating Token Index: 297

Text #1

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.8281. Min Act: -0.0000

Data Index: 1496205 (The Pile)

Max Activating Token Index: 506

Text #2

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.7291. Min Act: -0.0000

Data Index: 1593893 (The Pile)

Max Activating Token Index: 1020

Text #3

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.7028. Min Act: -0.0000

Data Index: 262992 (The Pile)

Max Activating Token Index: 958

Text #4

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.8758. Min Act: -0.0000

Data Index: 1875956 (The Pile)

Max Activating Token Index: 796

Text #5

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.7551. Min Act: -0.0000

Data Index: 1387230 (The Pile)

Max Activating Token Index: 662

Text #6

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.6641. Min Act: -0.0000

Data Index: 246930 (The Pile)

Max Activating Token Index: 518

Text #7

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.6476. Min Act: -0.0000

Data Index: 1174793 (The Pile)

Max Activating Token Index: 848

Text #8

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.5534. Min Act: -0.0000

Data Index: 492655 (The Pile)

Max Activating Token Index: 475

Text #9

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.7067. Min Act: -0.0000

Data Index: 1814162 (The Pile)

Max Activating Token Index: 855

Text #10

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.2970. Min Act: -0.0000

Data Index: 1154050 (The Pile)

Max Activating Token Index: 795

Text #11

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.3606. Min Act: -0.0000

Data Index: 480838 (The Pile)

Max Activating Token Index: 122

Text #12

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.4222. Min Act: -0.0000

Data Index: 361704 (The Pile)

Max Activating Token Index: 953

Text #13

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.4166. Min Act: -0.0000

Data Index: 21809 (The Pile)

Max Activating Token Index: 840

Text #14

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.4801. Min Act: -0.0000

Data Index: 971822 (The Pile)

Max Activating Token Index: 660

Text #15

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.4736. Min Act: -0.0000

Data Index: 1049668 (The Pile)

Max Activating Token Index: 972

Text #16

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.2996. Min Act: -0.0000

Data Index: 437133 (The Pile)

Max Activating Token Index: 747

Text #17

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.3004. Min Act: -0.0000

Data Index: 28583 (The Pile)

Max Activating Token Index: 702

Text #18

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.5374. Min Act: -0.0000

Data Index: 367742 (The Pile)

Max Activating Token Index: 842

Text #19

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.2868. Min Act: -0.0000

Data Index: 47534 (The Pile)

Max Activating Token Index: 873