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

Dataset: The Pile

Neuron 917 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: 1.8256. Min Range: -1.8256

Max Act: 1.7647. Min Act: -0.0000

Data Index: 772209 (The Pile)

Max Activating Token Index: 434

Text #1

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.8256. Min Act: -0.0000

Data Index: 1176214 (The Pile)

Max Activating Token Index: 361

Text #2

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.7441. Min Act: -0.0000

Data Index: 1552408 (The Pile)

Max Activating Token Index: 235

Text #3

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.6484. Min Act: -0.0000

Data Index: 1394210 (The Pile)

Max Activating Token Index: 586

Text #4

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.7200. Min Act: -0.0000

Data Index: 1993880 (The Pile)

Max Activating Token Index: 451

Text #5

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.6879. Min Act: -0.0000

Data Index: 1819076 (The Pile)

Max Activating Token Index: 539

Text #6

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.7832. Min Act: -0.0000

Data Index: 1834152 (The Pile)

Max Activating Token Index: 212

Text #7

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.7171. Min Act: -0.0000

Data Index: 1722314 (The Pile)

Max Activating Token Index: 642

Text #8

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.6536. Min Act: -0.0000

Data Index: 667977 (The Pile)

Max Activating Token Index: 361

Text #9

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.6532. Min Act: -0.0000

Data Index: 1345078 (The Pile)

Max Activating Token Index: 510

Text #10

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.6426. Min Act: -0.0000

Data Index: 1513101 (The Pile)

Max Activating Token Index: 716

Text #11

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.6569. Min Act: -0.0000

Data Index: 672893 (The Pile)

Max Activating Token Index: 626

Text #12

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.6300. Min Act: -0.0000

Data Index: 697977 (The Pile)

Max Activating Token Index: 768

Text #13

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.6293. Min Act: -0.0000

Data Index: 1255188 (The Pile)

Max Activating Token Index: 591

Text #14

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.5193. Min Act: -0.0000

Data Index: 437163 (The Pile)

Max Activating Token Index: 525

Text #15

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.5104. Min Act: -0.0000

Data Index: 472800 (The Pile)

Max Activating Token Index: 511

Text #16

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.5112. Min Act: -0.0000

Data Index: 883666 (The Pile)

Max Activating Token Index: 740

Text #17

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.5706. Min Act: -0.0000

Data Index: 1807700 (The Pile)

Max Activating Token Index: 651

Text #18

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.5049. Min Act: -0.0000

Data Index: 257901 (The Pile)

Max Activating Token Index: 145

Text #19

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.5983. Min Act: -0.0000

Data Index: 1693197 (The Pile)

Max Activating Token Index: 595