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

Dataset: The Pile

Neuron 2637 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.7847. Min Act: -0.0000

Data Index: 1001990 (The Pile)

Max Activating Token Index: 818

Text #1

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.7715. Min Act: -0.0000

Data Index: 1164406 (The Pile)

Max Activating Token Index: 913

Text #2

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.7273. Min Act: -0.0000

Data Index: 1534820 (The Pile)

Max Activating Token Index: 275

Text #3

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6483. Min Act: -0.0000

Data Index: 381675 (The Pile)

Max Activating Token Index: 210

Text #4

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6518. Min Act: -0.0000

Data Index: 415222 (The Pile)

Max Activating Token Index: 885

Text #5

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6645. Min Act: -0.0000

Data Index: 621617 (The Pile)

Max Activating Token Index: 816

Text #6

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.7237. Min Act: -0.0000

Data Index: 685540 (The Pile)

Max Activating Token Index: 532

Text #7

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6693. Min Act: -0.0000

Data Index: 1481247 (The Pile)

Max Activating Token Index: 1020

Text #8

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6553. Min Act: -0.0000

Data Index: 1627030 (The Pile)

Max Activating Token Index: 645

Text #9

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.5601. Min Act: -0.0000

Data Index: 430649 (The Pile)

Max Activating Token Index: 650

Text #10

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6464. Min Act: -0.0000

Data Index: 1931769 (The Pile)

Max Activating Token Index: 732

Text #11

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6526. Min Act: -0.0000

Data Index: 1902615 (The Pile)

Max Activating Token Index: 16

Text #12

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.5710. Min Act: -0.0000

Data Index: 16219 (The Pile)

Max Activating Token Index: 784

Text #13

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.5772. Min Act: -0.0000

Data Index: 190865 (The Pile)

Max Activating Token Index: 778

Text #14

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6342. Min Act: -0.0000

Data Index: 107507 (The Pile)

Max Activating Token Index: 789

Text #15

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6159. Min Act: -0.0000

Data Index: 528099 (The Pile)

Max Activating Token Index: 657

Text #16

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6381. Min Act: -0.0000

Data Index: 414085 (The Pile)

Max Activating Token Index: 780

Text #17

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6547. Min Act: -0.0000

Data Index: 1762320 (The Pile)

Max Activating Token Index: 994

Text #18

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6342. Min Act: -0.0000

Data Index: 1403963 (The Pile)

Max Activating Token Index: 1001

Text #19

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6757. Min Act: -0.0001

Data Index: 417577 (The Pile)

Max Activating Token Index: 787