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

Dataset: The Pile

Neuron 1575 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: 3.1750. Min Range: -3.1750

Max Act: 3.1750. Min Act: -0.0000

Data Index: 643818 (The Pile)

Max Activating Token Index: 99

Text #1

Max Range: 3.1750. Min Range: -3.1750

Max Act: 3.1479. Min Act: -0.0000

Data Index: 1799700 (The Pile)

Max Activating Token Index: 221

Text #2

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.9807. Min Act: -0.0000

Data Index: 1192963 (The Pile)

Max Activating Token Index: 144

Text #3

Max Range: 3.1750. Min Range: -3.1750

Max Act: 3.1317. Min Act: -0.0000

Data Index: 342935 (The Pile)

Max Activating Token Index: 132

Text #4

Max Range: 3.1750. Min Range: -3.1750

Max Act: 3.0692. Min Act: -0.0000

Data Index: 1509129 (The Pile)

Max Activating Token Index: 472

Text #5

Max Range: 3.1750. Min Range: -3.1750

Max Act: 3.0304. Min Act: -0.0000

Data Index: 1977731 (The Pile)

Max Activating Token Index: 19

Text #6

Max Range: 3.1750. Min Range: -3.1750

Max Act: 3.0484. Min Act: -0.0000

Data Index: 1527608 (The Pile)

Max Activating Token Index: 793

Text #7

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.7276. Min Act: -0.0000

Data Index: 361324 (The Pile)

Max Activating Token Index: 103

Text #8

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.8892. Min Act: -0.0000

Data Index: 1131725 (The Pile)

Max Activating Token Index: 70

Text #9

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.8167. Min Act: -0.0000

Data Index: 869878 (The Pile)

Max Activating Token Index: 366

Text #10

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.8147. Min Act: -0.0000

Data Index: 561234 (The Pile)

Max Activating Token Index: 333

Text #11

Max Range: 3.1750. Min Range: -3.1750

Max Act: 3.1001. Min Act: -0.0000

Data Index: 1557818 (The Pile)

Max Activating Token Index: 833

Text #12

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.9096. Min Act: -0.0000

Data Index: 1265695 (The Pile)

Max Activating Token Index: 393

Text #13

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.8823. Min Act: -0.0000

Data Index: 36764 (The Pile)

Max Activating Token Index: 349

Text #14

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.7173. Min Act: -0.0000

Data Index: 1659674 (The Pile)

Max Activating Token Index: 506

Text #15

Max Range: 3.1750. Min Range: -3.1750

Max Act: 3.0135. Min Act: -0.0000

Data Index: 1773716 (The Pile)

Max Activating Token Index: 289

Text #16

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.5896. Min Act: -0.0000

Data Index: 1233596 (The Pile)

Max Activating Token Index: 210

Text #17

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.8711. Min Act: -0.0000

Data Index: 339397 (The Pile)

Max Activating Token Index: 105

Text #18

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.8376. Min Act: -0.0000

Data Index: 1070646 (The Pile)

Max Activating Token Index: 248

Text #19

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.9618. Min Act: -0.0000

Data Index: 184656 (The Pile)

Max Activating Token Index: 126