Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 978 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.5109. Min Act: -0.0000

Data Index: 1905275 (The Pile)

Max Activating Token Index: 79

Text #1

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4333. Min Act: -0.0000

Data Index: 1072233 (The Pile)

Max Activating Token Index: 63

Text #2

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3895. Min Act: -0.0000

Data Index: 1945931 (The Pile)

Max Activating Token Index: 612

Text #3

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4125. Min Act: -0.0000

Data Index: 650744 (The Pile)

Max Activating Token Index: 532

Text #4

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3748. Min Act: -0.0000

Data Index: 527287 (The Pile)

Max Activating Token Index: 536

Text #5

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3682. Min Act: -0.0000

Data Index: 1826427 (The Pile)

Max Activating Token Index: 369

Text #6

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3693. Min Act: -0.0000

Data Index: 1764856 (The Pile)

Max Activating Token Index: 858

Text #7

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3829. Min Act: -0.0000

Data Index: 1013216 (The Pile)

Max Activating Token Index: 321

Text #8

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3591. Min Act: -0.0000

Data Index: 1979403 (The Pile)

Max Activating Token Index: 643

Text #9

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3080. Min Act: -0.0000

Data Index: 1201632 (The Pile)

Max Activating Token Index: 648

Text #10

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3642. Min Act: -0.0000

Data Index: 1809484 (The Pile)

Max Activating Token Index: 65

Text #11

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3382. Min Act: -0.0000

Data Index: 243322 (The Pile)

Max Activating Token Index: 633

Text #12

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3617. Min Act: -0.0000

Data Index: 157119 (The Pile)

Max Activating Token Index: 823

Text #13

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3586. Min Act: -0.0000

Data Index: 1797071 (The Pile)

Max Activating Token Index: 329

Text #14

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3617. Min Act: -0.0000

Data Index: 1985613 (The Pile)

Max Activating Token Index: 78

Text #15

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3324. Min Act: -0.0000

Data Index: 82855 (The Pile)

Max Activating Token Index: 609

Text #16

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3536. Min Act: -0.0000

Data Index: 666712 (The Pile)

Max Activating Token Index: 665

Text #17

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3495. Min Act: -0.0000

Data Index: 313554 (The Pile)

Max Activating Token Index: 738

Text #18

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3681. Min Act: -0.0000

Data Index: 1180939 (The Pile)

Max Activating Token Index: 611

Text #19

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3152. Min Act: -0.0000

Data Index: 1098446 (The Pile)

Max Activating Token Index: 160