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

Dataset: The Pile

Neuron 2758 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: 1.6229. Min Range: -1.6229

Max Act: 1.6229. Min Act: -0.0000

Data Index: 406217 (The Pile)

Max Activating Token Index: 39

Text #1

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.1656. Min Act: -0.0000

Data Index: 446453 (The Pile)

Max Activating Token Index: 454

Text #2

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.1535. Min Act: -0.0000

Data Index: 1207262 (The Pile)

Max Activating Token Index: 33

Text #3

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.0858. Min Act: -0.0000

Data Index: 1219130 (The Pile)

Max Activating Token Index: 203

Text #4

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.1273. Min Act: -0.0000

Data Index: 873115 (The Pile)

Max Activating Token Index: 354

Text #5

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.1807. Min Act: -0.0000

Data Index: 399927 (The Pile)

Max Activating Token Index: 850

Text #6

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.0077. Min Act: -0.0000

Data Index: 1535842 (The Pile)

Max Activating Token Index: 920

Text #7

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.0774. Min Act: -0.0000

Data Index: 1904593 (The Pile)

Max Activating Token Index: 47

Text #8

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.0035. Min Act: -0.0000

Data Index: 1515765 (The Pile)

Max Activating Token Index: 50

Text #9

Max Range: 1.6229. Min Range: -1.6229

Max Act: 0.9758. Min Act: -0.0000

Data Index: 130589 (The Pile)

Max Activating Token Index: 946

Text #10

Max Range: 1.6229. Min Range: -1.6229

Max Act: 0.9815. Min Act: -0.0000

Data Index: 1908475 (The Pile)

Max Activating Token Index: 547

Text #11

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.0403. Min Act: -0.0000

Data Index: 525765 (The Pile)

Max Activating Token Index: 631

Text #12

Max Range: 1.6229. Min Range: -1.6229

Max Act: 0.9672. Min Act: -0.0000

Data Index: 1600905 (The Pile)

Max Activating Token Index: 411

Text #13

Max Range: 1.6229. Min Range: -1.6229

Max Act: 0.9277. Min Act: -0.0000

Data Index: 927105 (The Pile)

Max Activating Token Index: 945

Text #14

Max Range: 1.6229. Min Range: -1.6229

Max Act: 0.9576. Min Act: -0.0000

Data Index: 1205754 (The Pile)

Max Activating Token Index: 785

Text #15

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.0263. Min Act: -0.0000

Data Index: 1766549 (The Pile)

Max Activating Token Index: 781

Text #16

Max Range: 1.6229. Min Range: -1.6229

Max Act: 0.9267. Min Act: -0.0000

Data Index: 37430 (The Pile)

Max Activating Token Index: 40

Text #17

Max Range: 1.6229. Min Range: -1.6229

Max Act: 0.8395. Min Act: -0.0000

Data Index: 1077195 (The Pile)

Max Activating Token Index: 24

Text #18

Max Range: 1.6229. Min Range: -1.6229

Max Act: 0.9470. Min Act: -0.0000

Data Index: 1201158 (The Pile)

Max Activating Token Index: 231

Text #19

Max Range: 1.6229. Min Range: -1.6229

Max Act: 0.8595. Min Act: -0.0000

Data Index: 604617 (The Pile)

Max Activating Token Index: 588