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

Dataset: The Pile

Neuron 4811 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: 3.2006. Min Range: -3.2006

Max Act: 3.2006. Min Act: -0.0000

Data Index: 1002024 (The Pile)

Max Activating Token Index: 352

Text #1

Max Range: 3.2006. Min Range: -3.2006

Max Act: 2.9366. Min Act: -0.0000

Data Index: 489673 (The Pile)

Max Activating Token Index: 545

Text #2

Max Range: 3.2006. Min Range: -3.2006

Max Act: 3.1776. Min Act: -0.0000

Data Index: 1711767 (The Pile)

Max Activating Token Index: 487

Text #3

Max Range: 3.2006. Min Range: -3.2006

Max Act: 3.0135. Min Act: -0.0000

Data Index: 842579 (The Pile)

Max Activating Token Index: 511

Text #4

Max Range: 3.2006. Min Range: -3.2006

Max Act: 3.0069. Min Act: -0.0000

Data Index: 1387016 (The Pile)

Max Activating Token Index: 995

Text #5

Max Range: 3.2006. Min Range: -3.2006

Max Act: 2.9664. Min Act: -0.0000

Data Index: 426699 (The Pile)

Max Activating Token Index: 765

Text #6

Max Range: 3.2006. Min Range: -3.2006

Max Act: 2.6902. Min Act: -0.0000

Data Index: 1391172 (The Pile)

Max Activating Token Index: 140

Text #7

Max Range: 3.2006. Min Range: -3.2006

Max Act: 2.3726. Min Act: -0.0000

Data Index: 1085880 (The Pile)

Max Activating Token Index: 595

Text #8

Max Range: 3.2006. Min Range: -3.2006

Max Act: 2.6369. Min Act: -0.0000

Data Index: 1292496 (The Pile)

Max Activating Token Index: 953

Text #9

Max Range: 3.2006. Min Range: -3.2006

Max Act: 2.5058. Min Act: -0.0000

Data Index: 1847672 (The Pile)

Max Activating Token Index: 117

Text #10

Max Range: 3.2006. Min Range: -3.2006

Max Act: 2.5423. Min Act: -0.0000

Data Index: 1766597 (The Pile)

Max Activating Token Index: 196

Text #11

Max Range: 3.2006. Min Range: -3.2006

Max Act: 2.3850. Min Act: -0.0000

Data Index: 706822 (The Pile)

Max Activating Token Index: 521

Text #12

Max Range: 3.2006. Min Range: -3.2006

Max Act: 2.4975. Min Act: -0.0000

Data Index: 541387 (The Pile)

Max Activating Token Index: 283

Text #13

Max Range: 3.2006. Min Range: -3.2006

Max Act: 2.8728. Min Act: -0.0000

Data Index: 242492 (The Pile)

Max Activating Token Index: 936

Text #14

Max Range: 3.2006. Min Range: -3.2006

Max Act: 2.2215. Min Act: -0.0000

Data Index: 1055616 (The Pile)

Max Activating Token Index: 179

Text #15

Max Range: 3.2006. Min Range: -3.2006

Max Act: 2.5678. Min Act: -0.0000

Data Index: 114229 (The Pile)

Max Activating Token Index: 921

Text #16

Max Range: 3.2006. Min Range: -3.2006

Max Act: 2.1647. Min Act: -0.0000

Data Index: 272093 (The Pile)

Max Activating Token Index: 644

Text #17

Max Range: 3.2006. Min Range: -3.2006

Max Act: 2.4065. Min Act: -0.0000

Data Index: 433397 (The Pile)

Max Activating Token Index: 16

Text #18

Max Range: 3.2006. Min Range: -3.2006

Max Act: 2.2587. Min Act: -0.0000

Data Index: 106091 (The Pile)

Max Activating Token Index: 987

Text #19

Max Range: 3.2006. Min Range: -3.2006

Max Act: 2.3053. Min Act: -0.0000

Data Index: 951687 (The Pile)

Max Activating Token Index: 905