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

Dataset: The Pile

Neuron 2976 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: 0.8960. Min Range: -0.8960

Max Act: 0.8960. Min Act: -0.0000

Data Index: 1077990 (The Pile)

Max Activating Token Index: 502

Text #1

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.7540. Min Act: -0.0000

Data Index: 1546089 (The Pile)

Max Activating Token Index: 780

Text #2

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.7035. Min Act: -0.0000

Data Index: 428879 (The Pile)

Max Activating Token Index: 572

Text #3

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.7086. Min Act: -0.0000

Data Index: 432410 (The Pile)

Max Activating Token Index: 865

Text #4

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6407. Min Act: -0.0000

Data Index: 234801 (The Pile)

Max Activating Token Index: 254

Text #5

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6347. Min Act: -0.0000

Data Index: 763917 (The Pile)

Max Activating Token Index: 411

Text #6

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6276. Min Act: -0.0000

Data Index: 510832 (The Pile)

Max Activating Token Index: 697

Text #7

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.5615. Min Act: -0.0000

Data Index: 585961 (The Pile)

Max Activating Token Index: 324

Text #8

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.5922. Min Act: -0.0000

Data Index: 369966 (The Pile)

Max Activating Token Index: 812

Text #9

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.5849. Min Act: -0.0000

Data Index: 624686 (The Pile)

Max Activating Token Index: 447

Text #10

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.5919. Min Act: -0.0000

Data Index: 174733 (The Pile)

Max Activating Token Index: 166

Text #11

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6051. Min Act: -0.0000

Data Index: 1712061 (The Pile)

Max Activating Token Index: 247

Text #12

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.5737. Min Act: -0.0000

Data Index: 1437519 (The Pile)

Max Activating Token Index: 99

Text #13

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6255. Min Act: -0.0000

Data Index: 626362 (The Pile)

Max Activating Token Index: 800

Text #14

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.5053. Min Act: -0.0000

Data Index: 1650555 (The Pile)

Max Activating Token Index: 207

Text #15

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.5534. Min Act: -0.0000

Data Index: 186052 (The Pile)

Max Activating Token Index: 439

Text #16

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.5672. Min Act: -0.0000

Data Index: 1052766 (The Pile)

Max Activating Token Index: 545

Text #17

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.5561. Min Act: -0.0000

Data Index: 1348773 (The Pile)

Max Activating Token Index: 843

Text #18

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.5293. Min Act: -0.0000

Data Index: 1121422 (The Pile)

Max Activating Token Index: 358

Text #19

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.5287. Min Act: -0.0000

Data Index: 1010809 (The Pile)

Max Activating Token Index: 828