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

Dataset: The Pile

Neuron 1769 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5056. Min Range: -1.5056

Max Act: 1.5056. Min Act: -0.0000

Data Index: 988750 (The Pile)

Max Activating Token Index: 953

Text #1

Max Range: 1.5056. Min Range: -1.5056

Max Act: 1.0430. Min Act: -0.0000

Data Index: 1821996 (The Pile)

Max Activating Token Index: 594

Text #2

Max Range: 1.5056. Min Range: -1.5056

Max Act: 1.0213. Min Act: -0.0000

Data Index: 1345496 (The Pile)

Max Activating Token Index: 82

Text #3

Max Range: 1.5056. Min Range: -1.5056

Max Act: 1.1766. Min Act: -0.0000

Data Index: 951484 (The Pile)

Max Activating Token Index: 812

Text #4

Max Range: 1.5056. Min Range: -1.5056

Max Act: 1.0985. Min Act: -0.0000

Data Index: 672506 (The Pile)

Max Activating Token Index: 754

Text #5

Max Range: 1.5056. Min Range: -1.5056

Max Act: 0.9839. Min Act: -0.0000

Data Index: 1130444 (The Pile)

Max Activating Token Index: 384

Text #6

Max Range: 1.5056. Min Range: -1.5056

Max Act: 0.9562. Min Act: -0.0000

Data Index: 1048453 (The Pile)

Max Activating Token Index: 1001

Text #7

Max Range: 1.5056. Min Range: -1.5056

Max Act: 0.8980. Min Act: -0.0000

Data Index: 568211 (The Pile)

Max Activating Token Index: 626

Text #8

Max Range: 1.5056. Min Range: -1.5056

Max Act: 0.9993. Min Act: -0.0000

Data Index: 1729116 (The Pile)

Max Activating Token Index: 366

Text #9

Max Range: 1.5056. Min Range: -1.5056

Max Act: 0.9821. Min Act: -0.0000

Data Index: 525510 (The Pile)

Max Activating Token Index: 498

Text #10

Max Range: 1.5056. Min Range: -1.5056

Max Act: 0.9094. Min Act: -0.0000

Data Index: 601261 (The Pile)

Max Activating Token Index: 346

Text #11

Max Range: 1.5056. Min Range: -1.5056

Max Act: 0.7834. Min Act: -0.0000

Data Index: 1896884 (The Pile)

Max Activating Token Index: 843

Text #12

Max Range: 1.5056. Min Range: -1.5056

Max Act: 0.9152. Min Act: -0.0000

Data Index: 1075103 (The Pile)

Max Activating Token Index: 900

Text #13

Max Range: 1.5056. Min Range: -1.5056

Max Act: 0.9220. Min Act: -0.0000

Data Index: 270363 (The Pile)

Max Activating Token Index: 265

Text #14

Max Range: 1.5056. Min Range: -1.5056

Max Act: 0.9720. Min Act: -0.0000

Data Index: 1725353 (The Pile)

Max Activating Token Index: 495

Text #15

Max Range: 1.5056. Min Range: -1.5056

Max Act: 0.8769. Min Act: -0.0000

Data Index: 1491941 (The Pile)

Max Activating Token Index: 111

Text #16

Max Range: 1.5056. Min Range: -1.5056

Max Act: 0.8126. Min Act: -0.0000

Data Index: 214666 (The Pile)

Max Activating Token Index: 410

Text #17

Max Range: 1.5056. Min Range: -1.5056

Max Act: 0.7192. Min Act: -0.0000

Data Index: 1486379 (The Pile)

Max Activating Token Index: 190

Text #18

Max Range: 1.5056. Min Range: -1.5056

Max Act: 0.8488. Min Act: -0.0000

Data Index: 1501841 (The Pile)

Max Activating Token Index: 979

Text #19

Max Range: 1.5056. Min Range: -1.5056

Max Act: 0.8895. Min Act: -0.0000

Data Index: 253189 (The Pile)

Max Activating Token Index: 864