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

Dataset: The Pile

Neuron 4033 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: 0.7099. Min Range: -0.7099

Max Act: 0.6548. Min Act: -0.0000

Data Index: 1433571 (The Pile)

Max Activating Token Index: 726

Text #1

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.7099. Min Act: -0.0000

Data Index: 1370726 (The Pile)

Max Activating Token Index: 570

Text #2

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.6203. Min Act: -0.0000

Data Index: 1376585 (The Pile)

Max Activating Token Index: 567

Text #3

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.6671. Min Act: -0.0000

Data Index: 423581 (The Pile)

Max Activating Token Index: 603

Text #4

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.6384. Min Act: -0.0000

Data Index: 1900054 (The Pile)

Max Activating Token Index: 241

Text #5

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5884. Min Act: -0.0000

Data Index: 1387732 (The Pile)

Max Activating Token Index: 231

Text #6

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.6040. Min Act: -0.0000

Data Index: 1908904 (The Pile)

Max Activating Token Index: 998

Text #7

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5608. Min Act: -0.0000

Data Index: 1276660 (The Pile)

Max Activating Token Index: 664

Text #8

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5404. Min Act: -0.0000

Data Index: 263646 (The Pile)

Max Activating Token Index: 641

Text #9

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.4796. Min Act: -0.0000

Data Index: 836476 (The Pile)

Max Activating Token Index: 667

Text #10

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5916. Min Act: -0.0000

Data Index: 1048089 (The Pile)

Max Activating Token Index: 193

Text #11

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5387. Min Act: -0.0000

Data Index: 1305832 (The Pile)

Max Activating Token Index: 702

Text #12

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5269. Min Act: -0.0000

Data Index: 95773 (The Pile)

Max Activating Token Index: 119

Text #13

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5615. Min Act: -0.0000

Data Index: 723899 (The Pile)

Max Activating Token Index: 87

Text #14

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.4757. Min Act: -0.0000

Data Index: 1489001 (The Pile)

Max Activating Token Index: 842

Text #15

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5417. Min Act: -0.0000

Data Index: 1632738 (The Pile)

Max Activating Token Index: 437

Text #16

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5051. Min Act: -0.0000

Data Index: 732559 (The Pile)

Max Activating Token Index: 761

Text #17

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5140. Min Act: -0.0000

Data Index: 1949711 (The Pile)

Max Activating Token Index: 625

Text #18

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5606. Min Act: -0.0000

Data Index: 231713 (The Pile)

Max Activating Token Index: 889

Text #19

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5483. Min Act: -0.0000

Data Index: 766505 (The Pile)

Max Activating Token Index: 664