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

Dataset: The Pile

Neuron 346 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.6377. Min Act: -0.0000

Data Index: 1377959 (The Pile)

Max Activating Token Index: 318

Text #1

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.5736. Min Act: -0.0000

Data Index: 453727 (The Pile)

Max Activating Token Index: 258

Text #2

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.5346. Min Act: -0.0000

Data Index: 907006 (The Pile)

Max Activating Token Index: 837

Text #3

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.5000. Min Act: -0.0000

Data Index: 1240728 (The Pile)

Max Activating Token Index: 67

Text #4

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.4115. Min Act: -0.0000

Data Index: 517978 (The Pile)

Max Activating Token Index: 534

Text #5

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.2759. Min Act: -0.0000

Data Index: 642797 (The Pile)

Max Activating Token Index: 875

Text #6

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.2163. Min Act: -0.0000

Data Index: 2779 (The Pile)

Max Activating Token Index: 136

Text #7

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.0587. Min Act: -0.0000

Data Index: 359103 (The Pile)

Max Activating Token Index: 954

Text #8

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.2744. Min Act: -0.0000

Data Index: 1224120 (The Pile)

Max Activating Token Index: 524

Text #9

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.0609. Min Act: -0.0000

Data Index: 1091340 (The Pile)

Max Activating Token Index: 192

Text #10

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.0435. Min Act: -0.0000

Data Index: 42005 (The Pile)

Max Activating Token Index: 495

Text #11

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.0867. Min Act: -0.0000

Data Index: 1133837 (The Pile)

Max Activating Token Index: 84

Text #12

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.1802. Min Act: -0.0000

Data Index: 195397 (The Pile)

Max Activating Token Index: 545

Text #13

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.0962. Min Act: -0.0000

Data Index: 1141404 (The Pile)

Max Activating Token Index: 185

Text #14

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.2305. Min Act: -0.0000

Data Index: 1012449 (The Pile)

Max Activating Token Index: 328

Text #15

Max Range: 1.6377. Min Range: -1.6377

Max Act: 0.9658. Min Act: -0.0000

Data Index: 1806434 (The Pile)

Max Activating Token Index: 982

Text #16

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.1268. Min Act: -0.0000

Data Index: 557112 (The Pile)

Max Activating Token Index: 55

Text #17

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.0090. Min Act: -0.0000

Data Index: 1920369 (The Pile)

Max Activating Token Index: 495

Text #18

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.0669. Min Act: -0.0000

Data Index: 1034122 (The Pile)

Max Activating Token Index: 947

Text #19

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.0007. Min Act: -0.0000

Data Index: 1838013 (The Pile)

Max Activating Token Index: 57