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

Dataset: The Pile

Neuron 1516 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.8267. Min Act: -0.0000

Data Index: 422896 (The Pile)

Max Activating Token Index: 887

Text #1

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.6802. Min Act: -0.0000

Data Index: 687418 (The Pile)

Max Activating Token Index: 863

Text #2

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.6026. Min Act: -0.0000

Data Index: 785311 (The Pile)

Max Activating Token Index: 861

Text #3

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.5434. Min Act: -0.0000

Data Index: 542881 (The Pile)

Max Activating Token Index: 651

Text #4

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.5589. Min Act: -0.0000

Data Index: 131630 (The Pile)

Max Activating Token Index: 670

Text #5

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.5644. Min Act: -0.0000

Data Index: 346271 (The Pile)

Max Activating Token Index: 157

Text #6

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.5224. Min Act: -0.0000

Data Index: 1217166 (The Pile)

Max Activating Token Index: 747

Text #7

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.4888. Min Act: -0.0000

Data Index: 1982895 (The Pile)

Max Activating Token Index: 1003

Text #8

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.5383. Min Act: -0.0000

Data Index: 1841175 (The Pile)

Max Activating Token Index: 723

Text #9

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.5293. Min Act: -0.0000

Data Index: 814206 (The Pile)

Max Activating Token Index: 643

Text #10

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.5285. Min Act: -0.0000

Data Index: 1863339 (The Pile)

Max Activating Token Index: 997

Text #11

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.5734. Min Act: -0.0000

Data Index: 737446 (The Pile)

Max Activating Token Index: 887

Text #12

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.5182. Min Act: -0.0000

Data Index: 526339 (The Pile)

Max Activating Token Index: 74

Text #13

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.5237. Min Act: -0.0000

Data Index: 361163 (The Pile)

Max Activating Token Index: 752

Text #14

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.4706. Min Act: -0.0000

Data Index: 533876 (The Pile)

Max Activating Token Index: 704

Text #15

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.5297. Min Act: -0.0000

Data Index: 955229 (The Pile)

Max Activating Token Index: 695

Text #16

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.5058. Min Act: -0.0000

Data Index: 1637728 (The Pile)

Max Activating Token Index: 64

Text #17

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.4855. Min Act: -0.0000

Data Index: 751993 (The Pile)

Max Activating Token Index: 473

Text #18

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.5054. Min Act: -0.0000

Data Index: 1080919 (The Pile)

Max Activating Token Index: 85

Text #19

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.4834. Min Act: -0.0000

Data Index: 1557301 (The Pile)

Max Activating Token Index: 174