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

Dataset: The Pile

Neuron 3339 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: 1.2703. Min Range: -1.2703

Max Act: 1.2316. Min Act: -0.0000

Data Index: 189745 (The Pile)

Max Activating Token Index: 264

Text #1

Max Range: 1.2703. Min Range: -1.2703

Max Act: 1.0970. Min Act: -0.0000

Data Index: 1294615 (The Pile)

Max Activating Token Index: 832

Text #2

Max Range: 1.2703. Min Range: -1.2703

Max Act: 1.2703. Min Act: -0.0000

Data Index: 184668 (The Pile)

Max Activating Token Index: 268

Text #3

Max Range: 1.2703. Min Range: -1.2703

Max Act: 1.1907. Min Act: -0.0000

Data Index: 1512127 (The Pile)

Max Activating Token Index: 133

Text #4

Max Range: 1.2703. Min Range: -1.2703

Max Act: 1.2192. Min Act: -0.0000

Data Index: 280186 (The Pile)

Max Activating Token Index: 7

Text #5

Max Range: 1.2703. Min Range: -1.2703

Max Act: 1.2261. Min Act: -0.0000

Data Index: 282651 (The Pile)

Max Activating Token Index: 216

Text #6

Max Range: 1.2703. Min Range: -1.2703

Max Act: 1.1610. Min Act: -0.0000

Data Index: 970461 (The Pile)

Max Activating Token Index: 480

Text #7

Max Range: 1.2703. Min Range: -1.2703

Max Act: 1.1228. Min Act: -0.0000

Data Index: 119108 (The Pile)

Max Activating Token Index: 436

Text #8

Max Range: 1.2703. Min Range: -1.2703

Max Act: 1.0910. Min Act: -0.0000

Data Index: 1220920 (The Pile)

Max Activating Token Index: 592

Text #9

Max Range: 1.2703. Min Range: -1.2703

Max Act: 1.1098. Min Act: -0.0000

Data Index: 380516 (The Pile)

Max Activating Token Index: 945

Text #10

Max Range: 1.2703. Min Range: -1.2703

Max Act: 1.2010. Min Act: -0.0000

Data Index: 709860 (The Pile)

Max Activating Token Index: 523

Text #11

Max Range: 1.2703. Min Range: -1.2703

Max Act: 1.1108. Min Act: -0.0000

Data Index: 1834930 (The Pile)

Max Activating Token Index: 13

Text #12

Max Range: 1.2703. Min Range: -1.2703

Max Act: 1.1789. Min Act: -0.0000

Data Index: 1919566 (The Pile)

Max Activating Token Index: 660

Text #13

Max Range: 1.2703. Min Range: -1.2703

Max Act: 0.8573. Min Act: -0.0000

Data Index: 1469202 (The Pile)

Max Activating Token Index: 811

Text #14

Max Range: 1.2703. Min Range: -1.2703

Max Act: 0.9864. Min Act: -0.0000

Data Index: 1688503 (The Pile)

Max Activating Token Index: 656

Text #15

Max Range: 1.2703. Min Range: -1.2703

Max Act: 1.0146. Min Act: -0.0000

Data Index: 943321 (The Pile)

Max Activating Token Index: 10

Text #16

Max Range: 1.2703. Min Range: -1.2703

Max Act: 1.0421. Min Act: -0.0000

Data Index: 590689 (The Pile)

Max Activating Token Index: 360

Text #17

Max Range: 1.2703. Min Range: -1.2703

Max Act: 1.1737. Min Act: -0.0000

Data Index: 1803294 (The Pile)

Max Activating Token Index: 418

Text #18

Max Range: 1.2703. Min Range: -1.2703

Max Act: 0.9852. Min Act: -0.0000

Data Index: 234484 (The Pile)

Max Activating Token Index: 794

Text #19

Max Range: 1.2703. Min Range: -1.2703

Max Act: 0.9745. Min Act: -0.0000

Data Index: 1141542 (The Pile)

Max Activating Token Index: 464