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

Dataset: The Pile

Neuron 3756 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: 0.7210. Min Range: -0.7210

Max Act: 0.7210. Min Act: -0.0000

Data Index: 1099661 (The Pile)

Max Activating Token Index: 443

Text #1

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.5598. Min Act: -0.0000

Data Index: 91090 (The Pile)

Max Activating Token Index: 141

Text #2

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.5763. Min Act: -0.0000

Data Index: 821353 (The Pile)

Max Activating Token Index: 1014

Text #3

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.5282. Min Act: -0.0000

Data Index: 1982296 (The Pile)

Max Activating Token Index: 775

Text #4

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.5356. Min Act: -0.0000

Data Index: 1587813 (The Pile)

Max Activating Token Index: 259

Text #5

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.4736. Min Act: -0.0000

Data Index: 1569674 (The Pile)

Max Activating Token Index: 610

Text #6

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.3901. Min Act: -0.0000

Data Index: 797025 (The Pile)

Max Activating Token Index: 713

Text #7

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.4245. Min Act: -0.0000

Data Index: 225865 (The Pile)

Max Activating Token Index: 742

Text #8

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.4098. Min Act: -0.0000

Data Index: 1322088 (The Pile)

Max Activating Token Index: 769

Text #9

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.4014. Min Act: -0.0000

Data Index: 1441247 (The Pile)

Max Activating Token Index: 306

Text #10

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.3839. Min Act: -0.0000

Data Index: 988057 (The Pile)

Max Activating Token Index: 521

Text #11

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.4386. Min Act: -0.0000

Data Index: 602691 (The Pile)

Max Activating Token Index: 959

Text #12

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.4049. Min Act: -0.0000

Data Index: 1110726 (The Pile)

Max Activating Token Index: 376

Text #13

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.3930. Min Act: -0.0000

Data Index: 207906 (The Pile)

Max Activating Token Index: 771

Text #14

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.3891. Min Act: -0.0000

Data Index: 585791 (The Pile)

Max Activating Token Index: 103

Text #15

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.4343. Min Act: -0.0000

Data Index: 1500376 (The Pile)

Max Activating Token Index: 763

Text #16

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.3813. Min Act: -0.0000

Data Index: 1708591 (The Pile)

Max Activating Token Index: 343

Text #17

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.4178. Min Act: -0.0000

Data Index: 1418150 (The Pile)

Max Activating Token Index: 834

Text #18

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.3469. Min Act: -0.0000

Data Index: 1940406 (The Pile)

Max Activating Token Index: 558

Text #19

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.3879. Min Act: -0.0000

Data Index: 898727 (The Pile)

Max Activating Token Index: 481