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

Dataset: The Pile

Neuron 1485 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: 0.9906. Min Range: -0.9906

Max Act: 0.9649. Min Act: -0.0000

Data Index: 1557011 (The Pile)

Max Activating Token Index: 204

Text #1

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.8194. Min Act: -0.0000

Data Index: 1513367 (The Pile)

Max Activating Token Index: 573

Text #2

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.6785. Min Act: -0.0000

Data Index: 1917400 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.8424. Min Act: -0.0000

Data Index: 753884 (The Pile)

Max Activating Token Index: 397

Text #4

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.7504. Min Act: -0.0000

Data Index: 204635 (The Pile)

Max Activating Token Index: 73

Text #5

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.8538. Min Act: -0.0000

Data Index: 1211561 (The Pile)

Max Activating Token Index: 529

Text #6

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.8417. Min Act: -0.0000

Data Index: 838946 (The Pile)

Max Activating Token Index: 242

Text #7

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.9044. Min Act: -0.0000

Data Index: 1842913 (The Pile)

Max Activating Token Index: 180

Text #8

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.7582. Min Act: -0.0000

Data Index: 1864402 (The Pile)

Max Activating Token Index: 67

Text #9

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.7832. Min Act: -0.0000

Data Index: 660855 (The Pile)

Max Activating Token Index: 963

Text #10

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.9906. Min Act: -0.0000

Data Index: 1622653 (The Pile)

Max Activating Token Index: 887

Text #11

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.8010. Min Act: -0.0000

Data Index: 663546 (The Pile)

Max Activating Token Index: 737

Text #12

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.6889. Min Act: -0.0000

Data Index: 404637 (The Pile)

Max Activating Token Index: 168

Text #13

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.7238. Min Act: -0.0000

Data Index: 389967 (The Pile)

Max Activating Token Index: 588

Text #14

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.7778. Min Act: -0.0000

Data Index: 152494 (The Pile)

Max Activating Token Index: 1007

Text #15

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.7441. Min Act: -0.0000

Data Index: 1971817 (The Pile)

Max Activating Token Index: 635

Text #16

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.7118. Min Act: -0.0000

Data Index: 1839773 (The Pile)

Max Activating Token Index: 428

Text #17

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.6825. Min Act: -0.0000

Data Index: 106520 (The Pile)

Max Activating Token Index: 951

Text #18

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.7083. Min Act: -0.0000

Data Index: 642608 (The Pile)

Max Activating Token Index: 755

Text #19

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.6673. Min Act: -0.0000

Data Index: 436030 (The Pile)

Max Activating Token Index: 199