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

Dataset: The Pile

Neuron 2589 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: 0.7870. Min Range: -0.7870

Max Act: 0.7551. Min Act: -0.0000

Data Index: 816585 (The Pile)

Max Activating Token Index: 996

Text #1

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.7832. Min Act: -0.0000

Data Index: 1362871 (The Pile)

Max Activating Token Index: 968

Text #2

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.7870. Min Act: -0.0000

Data Index: 1589891 (The Pile)

Max Activating Token Index: 259

Text #3

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.6872. Min Act: -0.0000

Data Index: 647441 (The Pile)

Max Activating Token Index: 13

Text #4

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.7510. Min Act: -0.0000

Data Index: 1290185 (The Pile)

Max Activating Token Index: 331

Text #5

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.6938. Min Act: -0.0000

Data Index: 1820189 (The Pile)

Max Activating Token Index: 509

Text #6

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.7162. Min Act: -0.0000

Data Index: 1134754 (The Pile)

Max Activating Token Index: 536

Text #7

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.7088. Min Act: -0.0000

Data Index: 251019 (The Pile)

Max Activating Token Index: 791

Text #8

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.7395. Min Act: -0.0000

Data Index: 1245990 (The Pile)

Max Activating Token Index: 777

Text #9

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.7102. Min Act: -0.0000

Data Index: 1795627 (The Pile)

Max Activating Token Index: 599

Text #10

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.6669. Min Act: -0.0000

Data Index: 747056 (The Pile)

Max Activating Token Index: 130

Text #11

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.7146. Min Act: -0.0000

Data Index: 907513 (The Pile)

Max Activating Token Index: 61

Text #12

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.5954. Min Act: -0.0000

Data Index: 469733 (The Pile)

Max Activating Token Index: 83

Text #13

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.6962. Min Act: -0.0000

Data Index: 1578659 (The Pile)

Max Activating Token Index: 172

Text #14

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.6499. Min Act: -0.0000

Data Index: 1519281 (The Pile)

Max Activating Token Index: 833

Text #15

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.6728. Min Act: -0.0000

Data Index: 167705 (The Pile)

Max Activating Token Index: 896

Text #16

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.6406. Min Act: -0.0000

Data Index: 210987 (The Pile)

Max Activating Token Index: 814

Text #17

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.6607. Min Act: -0.0000

Data Index: 1783919 (The Pile)

Max Activating Token Index: 412

Text #18

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.6065. Min Act: -0.0000

Data Index: 1044305 (The Pile)

Max Activating Token Index: 127

Text #19

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.6507. Min Act: -0.0000

Data Index: 1365139 (The Pile)

Max Activating Token Index: 986