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

Dataset: The Pile

Neuron 4006 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0066. Min Act: -0.0000

Data Index: 1334476 (The Pile)

Max Activating Token Index: 356

Text #1

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0044. Min Act: -0.0000

Data Index: 1214389 (The Pile)

Max Activating Token Index: 388

Text #2

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0035. Min Act: -0.0000

Data Index: 4953 (The Pile)

Max Activating Token Index: 455

Text #3

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0044. Min Act: -0.0000

Data Index: 840761 (The Pile)

Max Activating Token Index: 161

Text #4

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0033. Min Act: -0.0000

Data Index: 1594669 (The Pile)

Max Activating Token Index: 455

Text #5

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0039. Min Act: -0.0000

Data Index: 1574411 (The Pile)

Max Activating Token Index: 452

Text #6

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0026. Min Act: -0.0000

Data Index: 1314144 (The Pile)

Max Activating Token Index: 770

Text #7

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0021. Min Act: -0.0000

Data Index: 735122 (The Pile)

Max Activating Token Index: 446

Text #8

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0005. Min Act: -0.0000

Data Index: 1532387 (The Pile)

Max Activating Token Index: 990

Text #9

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0020. Min Act: -0.0000

Data Index: 296109 (The Pile)

Max Activating Token Index: 554

Text #10

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0021. Min Act: -0.0000

Data Index: 386992 (The Pile)

Max Activating Token Index: 720

Text #11

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0019. Min Act: -0.0000

Data Index: 12198 (The Pile)

Max Activating Token Index: 209

Text #12

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0018. Min Act: -0.0000

Data Index: 1050174 (The Pile)

Max Activating Token Index: 469

Text #13

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0019. Min Act: -0.0000

Data Index: 518765 (The Pile)

Max Activating Token Index: 342

Text #14

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0014. Min Act: -0.0000

Data Index: 843051 (The Pile)

Max Activating Token Index: 737

Text #15

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0015. Min Act: -0.0000

Data Index: 1230255 (The Pile)

Max Activating Token Index: 630

Text #16

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0014. Min Act: -0.0000

Data Index: 718191 (The Pile)

Max Activating Token Index: 819

Text #17

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0014. Min Act: -0.0000

Data Index: 880537 (The Pile)

Max Activating Token Index: 529

Text #18

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0014. Min Act: -0.0000

Data Index: 1950652 (The Pile)

Max Activating Token Index: 739

Text #19

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0011. Min Act: -0.0000

Data Index: 621593 (The Pile)

Max Activating Token Index: 696