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

Dataset: The Pile

Neuron 3457 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: 3.2803. Min Range: -3.2803

Max Act: 3.2803. Min Act: -0.0000

Data Index: 1831853 (The Pile)

Max Activating Token Index: 760

Text #1

Max Range: 3.2803. Min Range: -3.2803

Max Act: 2.3562. Min Act: -0.0000

Data Index: 337898 (The Pile)

Max Activating Token Index: 908

Text #2

Max Range: 3.2803. Min Range: -3.2803

Max Act: 2.1879. Min Act: -0.0000

Data Index: 976756 (The Pile)

Max Activating Token Index: 1009

Text #3

Max Range: 3.2803. Min Range: -3.2803

Max Act: 1.9927. Min Act: -0.0000

Data Index: 1246610 (The Pile)

Max Activating Token Index: 492

Text #4

Max Range: 3.2803. Min Range: -3.2803

Max Act: 2.2422. Min Act: -0.0000

Data Index: 251275 (The Pile)

Max Activating Token Index: 828

Text #5

Max Range: 3.2803. Min Range: -3.2803

Max Act: 2.0573. Min Act: -0.0000

Data Index: 1743697 (The Pile)

Max Activating Token Index: 996

Text #6

Max Range: 3.2803. Min Range: -3.2803

Max Act: 1.9464. Min Act: -0.0000

Data Index: 761866 (The Pile)

Max Activating Token Index: 105

Text #7

Max Range: 3.2803. Min Range: -3.2803

Max Act: 1.7964. Min Act: -0.0000

Data Index: 1642847 (The Pile)

Max Activating Token Index: 538

Text #8

Max Range: 3.2803. Min Range: -3.2803

Max Act: 1.7920. Min Act: -0.0000

Data Index: 1765569 (The Pile)

Max Activating Token Index: 972

Text #9

Max Range: 3.2803. Min Range: -3.2803

Max Act: 1.8765. Min Act: -0.0000

Data Index: 1073861 (The Pile)

Max Activating Token Index: 376

Text #10

Max Range: 3.2803. Min Range: -3.2803

Max Act: 2.0014. Min Act: -0.0000

Data Index: 200496 (The Pile)

Max Activating Token Index: 472

Text #11

Max Range: 3.2803. Min Range: -3.2803

Max Act: 1.9687. Min Act: -0.0000

Data Index: 1947847 (The Pile)

Max Activating Token Index: 361

Text #12

Max Range: 3.2803. Min Range: -3.2803

Max Act: 1.8301. Min Act: -0.0000

Data Index: 772753 (The Pile)

Max Activating Token Index: 331

Text #13

Max Range: 3.2803. Min Range: -3.2803

Max Act: 1.8798. Min Act: -0.0000

Data Index: 1637999 (The Pile)

Max Activating Token Index: 411

Text #14

Max Range: 3.2803. Min Range: -3.2803

Max Act: 1.8531. Min Act: -0.0000

Data Index: 158353 (The Pile)

Max Activating Token Index: 675

Text #15

Max Range: 3.2803. Min Range: -3.2803

Max Act: 1.9475. Min Act: -0.0000

Data Index: 1482182 (The Pile)

Max Activating Token Index: 585

Text #16

Max Range: 3.2803. Min Range: -3.2803

Max Act: 1.8166. Min Act: -0.0000

Data Index: 1410589 (The Pile)

Max Activating Token Index: 514

Text #17

Max Range: 3.2803. Min Range: -3.2803

Max Act: 1.7996. Min Act: -0.0000

Data Index: 1940727 (The Pile)

Max Activating Token Index: 802

Text #18

Max Range: 3.2803. Min Range: -3.2803

Max Act: 1.8262. Min Act: -0.0000

Data Index: 1756111 (The Pile)

Max Activating Token Index: 787

Text #19

Max Range: 3.2803. Min Range: -3.2803

Max Act: 1.7619. Min Act: -0.0000

Data Index: 912727 (The Pile)

Max Activating Token Index: 214