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

Dataset: The Pile

Neuron 252 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: 1.2861. Min Range: -1.2861

Max Act: 1.2861. Min Act: -0.0000

Data Index: 1179072 (The Pile)

Max Activating Token Index: 133

Text #1

Max Range: 1.2861. Min Range: -1.2861

Max Act: 1.0765. Min Act: -0.0000

Data Index: 1407535 (The Pile)

Max Activating Token Index: 593

Text #2

Max Range: 1.2861. Min Range: -1.2861

Max Act: 1.0694. Min Act: -0.0000

Data Index: 591023 (The Pile)

Max Activating Token Index: 660

Text #3

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.8999. Min Act: -0.0000

Data Index: 1127883 (The Pile)

Max Activating Token Index: 840

Text #4

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.8490. Min Act: -0.0000

Data Index: 1402682 (The Pile)

Max Activating Token Index: 252

Text #5

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.8538. Min Act: -0.0000

Data Index: 1398093 (The Pile)

Max Activating Token Index: 258

Text #6

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.8782. Min Act: -0.0000

Data Index: 1741914 (The Pile)

Max Activating Token Index: 201

Text #7

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.8732. Min Act: -0.0000

Data Index: 1624503 (The Pile)

Max Activating Token Index: 151

Text #8

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.8042. Min Act: -0.0000

Data Index: 424752 (The Pile)

Max Activating Token Index: 759

Text #9

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.8001. Min Act: -0.0000

Data Index: 1840063 (The Pile)

Max Activating Token Index: 391

Text #10

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.7821. Min Act: -0.0000

Data Index: 1040953 (The Pile)

Max Activating Token Index: 463

Text #11

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.7761. Min Act: -0.0000

Data Index: 1872268 (The Pile)

Max Activating Token Index: 786

Text #12

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.7756. Min Act: -0.0000

Data Index: 936274 (The Pile)

Max Activating Token Index: 459

Text #13

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.8102. Min Act: -0.0000

Data Index: 1403304 (The Pile)

Max Activating Token Index: 717

Text #14

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.7642. Min Act: -0.0000

Data Index: 1523612 (The Pile)

Max Activating Token Index: 224

Text #15

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.8141. Min Act: -0.0000

Data Index: 1608030 (The Pile)

Max Activating Token Index: 227

Text #16

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.6870. Min Act: -0.0000

Data Index: 1614489 (The Pile)

Max Activating Token Index: 658

Text #17

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.7691. Min Act: -0.0000

Data Index: 90367 (The Pile)

Max Activating Token Index: 481

Text #18

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.7478. Min Act: -0.0000

Data Index: 110795 (The Pile)

Max Activating Token Index: 398

Text #19

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.7132. Min Act: -0.0000

Data Index: 776001 (The Pile)

Max Activating Token Index: 98