Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2649 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0478. Min Range: -1.0478

Max Act: 1.0478. Min Act: -0.0000

Data Index: 1118279 (The Pile)

Max Activating Token Index: 534

Text #1

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.8703. Min Act: -0.0000

Data Index: 874097 (The Pile)

Max Activating Token Index: 608

Text #2

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.7699. Min Act: -0.0000

Data Index: 264638 (The Pile)

Max Activating Token Index: 841

Text #3

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.7943. Min Act: -0.0000

Data Index: 1346669 (The Pile)

Max Activating Token Index: 952

Text #4

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.7879. Min Act: -0.0000

Data Index: 668351 (The Pile)

Max Activating Token Index: 289

Text #5

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.5919. Min Act: -0.0000

Data Index: 314896 (The Pile)

Max Activating Token Index: 844

Text #6

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.6275. Min Act: -0.0000

Data Index: 569534 (The Pile)

Max Activating Token Index: 492

Text #7

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.5784. Min Act: -0.0000

Data Index: 917691 (The Pile)

Max Activating Token Index: 873

Text #8

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.5326. Min Act: -0.0000

Data Index: 1960275 (The Pile)

Max Activating Token Index: 295

Text #9

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.5964. Min Act: -0.0000

Data Index: 1693594 (The Pile)

Max Activating Token Index: 496

Text #10

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.5788. Min Act: -0.0000

Data Index: 705362 (The Pile)

Max Activating Token Index: 777

Text #11

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.5104. Min Act: -0.0000

Data Index: 597378 (The Pile)

Max Activating Token Index: 965

Text #12

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.5152. Min Act: -0.0000

Data Index: 24689 (The Pile)

Max Activating Token Index: 954

Text #13

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.5055. Min Act: -0.0000

Data Index: 1950429 (The Pile)

Max Activating Token Index: 233

Text #14

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.5000. Min Act: -0.0000

Data Index: 680339 (The Pile)

Max Activating Token Index: 998

Text #15

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.6161. Min Act: -0.0000

Data Index: 290179 (The Pile)

Max Activating Token Index: 376

Text #16

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.5055. Min Act: -0.0000

Data Index: 1252640 (The Pile)

Max Activating Token Index: 29

Text #17

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.5280. Min Act: -0.0000

Data Index: 1275473 (The Pile)

Max Activating Token Index: 569

Text #18

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.4781. Min Act: -0.0000

Data Index: 482808 (The Pile)

Max Activating Token Index: 443

Text #19

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.4979. Min Act: -0.0000

Data Index: 1100922 (The Pile)

Max Activating Token Index: 364