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

Dataset: The Pile

Neuron 1927 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.6865. Min Act: -0.0000

Data Index: 1726026 (The Pile)

Max Activating Token Index: 611

Text #1

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.6028. Min Act: -0.0000

Data Index: 1800909 (The Pile)

Max Activating Token Index: 798

Text #2

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.5907. Min Act: -0.0000

Data Index: 1945377 (The Pile)

Max Activating Token Index: 399

Text #3

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.5829. Min Act: -0.0000

Data Index: 1825048 (The Pile)

Max Activating Token Index: 393

Text #4

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.5202. Min Act: -0.0000

Data Index: 1806376 (The Pile)

Max Activating Token Index: 112

Text #5

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.5110. Min Act: -0.0000

Data Index: 1188519 (The Pile)

Max Activating Token Index: 674

Text #6

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.4733. Min Act: -0.0000

Data Index: 1063912 (The Pile)

Max Activating Token Index: 750

Text #7

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.4621. Min Act: -0.0000

Data Index: 487623 (The Pile)

Max Activating Token Index: 147

Text #8

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.4787. Min Act: -0.0000

Data Index: 324696 (The Pile)

Max Activating Token Index: 550

Text #9

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.4742. Min Act: -0.0000

Data Index: 1833018 (The Pile)

Max Activating Token Index: 154

Text #10

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.4674. Min Act: -0.0000

Data Index: 660420 (The Pile)

Max Activating Token Index: 213

Text #11

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.4814. Min Act: -0.0000

Data Index: 199614 (The Pile)

Max Activating Token Index: 758

Text #12

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.4431. Min Act: -0.0000

Data Index: 790020 (The Pile)

Max Activating Token Index: 1011

Text #13

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.4814. Min Act: -0.0000

Data Index: 1036253 (The Pile)

Max Activating Token Index: 894

Text #14

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.4518. Min Act: -0.0000

Data Index: 500070 (The Pile)

Max Activating Token Index: 496

Text #15

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.4195. Min Act: -0.0000

Data Index: 480152 (The Pile)

Max Activating Token Index: 876

Text #16

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.4583. Min Act: -0.0000

Data Index: 486461 (The Pile)

Max Activating Token Index: 653

Text #17

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.4403. Min Act: -0.0000

Data Index: 1137097 (The Pile)

Max Activating Token Index: 655

Text #18

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.4333. Min Act: -0.0000

Data Index: 736795 (The Pile)

Max Activating Token Index: 463

Text #19

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.4183. Min Act: -0.0000

Data Index: 1080490 (The Pile)

Max Activating Token Index: 317