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

Dataset: The Pile

Neuron 4703 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: 0.5112. Min Range: -0.5112

Max Act: 0.5035. Min Act: -0.0000

Data Index: 874803 (The Pile)

Max Activating Token Index: 543

Text #1

Max Range: 0.5112. Min Range: -0.5112

Max Act: 0.5112. Min Act: -0.0000

Data Index: 1301904 (The Pile)

Max Activating Token Index: 304

Text #2

Max Range: 0.5112. Min Range: -0.5112

Max Act: 0.3916. Min Act: -0.0000

Data Index: 1186546 (The Pile)

Max Activating Token Index: 811

Text #3

Max Range: 0.5112. Min Range: -0.5112

Max Act: 0.3575. Min Act: -0.0000

Data Index: 627930 (The Pile)

Max Activating Token Index: 783

Text #4

Max Range: 0.5112. Min Range: -0.5112

Max Act: 0.3292. Min Act: -0.0000

Data Index: 252837 (The Pile)

Max Activating Token Index: 620

Text #5

Max Range: 0.5112. Min Range: -0.5112

Max Act: 0.3200. Min Act: -0.0000

Data Index: 491996 (The Pile)

Max Activating Token Index: 378

Text #6

Max Range: 0.5112. Min Range: -0.5112

Max Act: 0.2909. Min Act: -0.0000

Data Index: 499577 (The Pile)

Max Activating Token Index: 1008

Text #7

Max Range: 0.5112. Min Range: -0.5112

Max Act: 0.2743. Min Act: -0.0000

Data Index: 666480 (The Pile)

Max Activating Token Index: 814

Text #8

Max Range: 0.5112. Min Range: -0.5112

Max Act: 0.2993. Min Act: -0.0000

Data Index: 1144108 (The Pile)

Max Activating Token Index: 864

Text #9

Max Range: 0.5112. Min Range: -0.5112

Max Act: 0.3083. Min Act: -0.0000

Data Index: 206981 (The Pile)

Max Activating Token Index: 315

Text #10

Max Range: 0.5112. Min Range: -0.5112

Max Act: 0.2812. Min Act: -0.0000

Data Index: 197685 (The Pile)

Max Activating Token Index: 951

Text #11

Max Range: 0.5112. Min Range: -0.5112

Max Act: 0.3282. Min Act: -0.0000

Data Index: 863441 (The Pile)

Max Activating Token Index: 817

Text #12

Max Range: 0.5112. Min Range: -0.5112

Max Act: 0.2918. Min Act: -0.0000

Data Index: 874152 (The Pile)

Max Activating Token Index: 291

Text #13

Max Range: 0.5112. Min Range: -0.5112

Max Act: 0.2761. Min Act: -0.0000

Data Index: 1140034 (The Pile)

Max Activating Token Index: 648

Text #14

Max Range: 0.5112. Min Range: -0.5112

Max Act: 0.2921. Min Act: -0.0000

Data Index: 1913847 (The Pile)

Max Activating Token Index: 224

Text #15

Max Range: 0.5112. Min Range: -0.5112

Max Act: 0.2883. Min Act: -0.0000

Data Index: 337798 (The Pile)

Max Activating Token Index: 836

Text #16

Max Range: 0.5112. Min Range: -0.5112

Max Act: 0.2810. Min Act: -0.0000

Data Index: 694993 (The Pile)

Max Activating Token Index: 553

Text #17

Max Range: 0.5112. Min Range: -0.5112

Max Act: 0.2662. Min Act: -0.0000

Data Index: 1885065 (The Pile)

Max Activating Token Index: 377

Text #18

Max Range: 0.5112. Min Range: -0.5112

Max Act: 0.3016. Min Act: -0.0000

Data Index: 1405837 (The Pile)

Max Activating Token Index: 63

Text #19

Max Range: 0.5112. Min Range: -0.5112

Max Act: 0.2825. Min Act: -0.0000

Data Index: 131149 (The Pile)

Max Activating Token Index: 792