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

Dataset: The Pile

Neuron 986 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: 1.6745. Min Range: -1.6745

Max Act: 1.6745. Min Act: -0.0000

Data Index: 1940324 (The Pile)

Max Activating Token Index: 592

Text #1

Max Range: 1.6745. Min Range: -1.6745

Max Act: 1.4286. Min Act: -0.0000

Data Index: 728770 (The Pile)

Max Activating Token Index: 465

Text #2

Max Range: 1.6745. Min Range: -1.6745

Max Act: 1.4358. Min Act: -0.0000

Data Index: 565181 (The Pile)

Max Activating Token Index: 233

Text #3

Max Range: 1.6745. Min Range: -1.6745

Max Act: 1.4271. Min Act: -0.0000

Data Index: 1391383 (The Pile)

Max Activating Token Index: 223

Text #4

Max Range: 1.6745. Min Range: -1.6745

Max Act: 1.3808. Min Act: -0.0000

Data Index: 900012 (The Pile)

Max Activating Token Index: 504

Text #5

Max Range: 1.6745. Min Range: -1.6745

Max Act: 1.5029. Min Act: -0.0000

Data Index: 714228 (The Pile)

Max Activating Token Index: 850

Text #6

Max Range: 1.6745. Min Range: -1.6745

Max Act: 1.3271. Min Act: -0.0000

Data Index: 1461782 (The Pile)

Max Activating Token Index: 519

Text #7

Max Range: 1.6745. Min Range: -1.6745

Max Act: 1.3298. Min Act: -0.0000

Data Index: 1463854 (The Pile)

Max Activating Token Index: 669

Text #8

Max Range: 1.6745. Min Range: -1.6745

Max Act: 1.3159. Min Act: -0.0000

Data Index: 1033078 (The Pile)

Max Activating Token Index: 544

Text #9

Max Range: 1.6745. Min Range: -1.6745

Max Act: 1.2980. Min Act: -0.0000

Data Index: 1526266 (The Pile)

Max Activating Token Index: 794

Text #10

Max Range: 1.6745. Min Range: -1.6745

Max Act: 1.3495. Min Act: -0.0000

Data Index: 370235 (The Pile)

Max Activating Token Index: 1005

Text #11

Max Range: 1.6745. Min Range: -1.6745

Max Act: 1.2951. Min Act: -0.0000

Data Index: 42249 (The Pile)

Max Activating Token Index: 976

Text #12

Max Range: 1.6745. Min Range: -1.6745

Max Act: 1.3311. Min Act: -0.0000

Data Index: 30978 (The Pile)

Max Activating Token Index: 520

Text #13

Max Range: 1.6745. Min Range: -1.6745

Max Act: 1.2896. Min Act: -0.0000

Data Index: 1615013 (The Pile)

Max Activating Token Index: 319

Text #14

Max Range: 1.6745. Min Range: -1.6745

Max Act: 1.2114. Min Act: -0.0000

Data Index: 154418 (The Pile)

Max Activating Token Index: 176

Text #15

Max Range: 1.6745. Min Range: -1.6745

Max Act: 1.2080. Min Act: -0.0000

Data Index: 642282 (The Pile)

Max Activating Token Index: 645

Text #16

Max Range: 1.6745. Min Range: -1.6745

Max Act: 1.2810. Min Act: -0.0000

Data Index: 1742123 (The Pile)

Max Activating Token Index: 386

Text #17

Max Range: 1.6745. Min Range: -1.6745

Max Act: 1.1959. Min Act: -0.0000

Data Index: 525641 (The Pile)

Max Activating Token Index: 649

Text #18

Max Range: 1.6745. Min Range: -1.6745

Max Act: 1.3049. Min Act: -0.0000

Data Index: 248984 (The Pile)

Max Activating Token Index: 480

Text #19

Max Range: 1.6745. Min Range: -1.6745

Max Act: 1.1843. Min Act: -0.0000

Data Index: 345689 (The Pile)

Max Activating Token Index: 975