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

Dataset: The Pile

Neuron 2622 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: 1.7372. Min Range: -1.7372

Max Act: 1.7372. Min Act: -0.0000

Data Index: 657309 (The Pile)

Max Activating Token Index: 209

Text #1

Max Range: 1.7372. Min Range: -1.7372

Max Act: 1.3727. Min Act: -0.0000

Data Index: 864227 (The Pile)

Max Activating Token Index: 492

Text #2

Max Range: 1.7372. Min Range: -1.7372

Max Act: 1.3392. Min Act: -0.0000

Data Index: 1189942 (The Pile)

Max Activating Token Index: 469

Text #3

Max Range: 1.7372. Min Range: -1.7372

Max Act: 1.3144. Min Act: -0.0000

Data Index: 850293 (The Pile)

Max Activating Token Index: 978

Text #4

Max Range: 1.7372. Min Range: -1.7372

Max Act: 1.2534. Min Act: -0.0000

Data Index: 1653439 (The Pile)

Max Activating Token Index: 761

Text #5

Max Range: 1.7372. Min Range: -1.7372

Max Act: 1.2547. Min Act: -0.0000

Data Index: 1218864 (The Pile)

Max Activating Token Index: 97

Text #6

Max Range: 1.7372. Min Range: -1.7372

Max Act: 1.0559. Min Act: -0.0000

Data Index: 881234 (The Pile)

Max Activating Token Index: 775

Text #7

Max Range: 1.7372. Min Range: -1.7372

Max Act: 1.2282. Min Act: -0.0000

Data Index: 1704244 (The Pile)

Max Activating Token Index: 442

Text #8

Max Range: 1.7372. Min Range: -1.7372

Max Act: 1.0412. Min Act: -0.0000

Data Index: 27577 (The Pile)

Max Activating Token Index: 641

Text #9

Max Range: 1.7372. Min Range: -1.7372

Max Act: 1.0870. Min Act: -0.0000

Data Index: 831122 (The Pile)

Max Activating Token Index: 869

Text #10

Max Range: 1.7372. Min Range: -1.7372

Max Act: 1.0737. Min Act: -0.0000

Data Index: 434599 (The Pile)

Max Activating Token Index: 771

Text #11

Max Range: 1.7372. Min Range: -1.7372

Max Act: 1.0479. Min Act: -0.0000

Data Index: 474630 (The Pile)

Max Activating Token Index: 152

Text #12

Max Range: 1.7372. Min Range: -1.7372

Max Act: 1.0200. Min Act: -0.0000

Data Index: 77333 (The Pile)

Max Activating Token Index: 633

Text #13

Max Range: 1.7372. Min Range: -1.7372

Max Act: 0.9783. Min Act: -0.0000

Data Index: 453609 (The Pile)

Max Activating Token Index: 760

Text #14

Max Range: 1.7372. Min Range: -1.7372

Max Act: 1.0290. Min Act: -0.0000

Data Index: 1821490 (The Pile)

Max Activating Token Index: 604

Text #15

Max Range: 1.7372. Min Range: -1.7372

Max Act: 1.0452. Min Act: -0.0000

Data Index: 1015105 (The Pile)

Max Activating Token Index: 944

Text #16

Max Range: 1.7372. Min Range: -1.7372

Max Act: 1.0668. Min Act: -0.0000

Data Index: 1490120 (The Pile)

Max Activating Token Index: 507

Text #17

Max Range: 1.7372. Min Range: -1.7372

Max Act: 0.9124. Min Act: -0.0000

Data Index: 989242 (The Pile)

Max Activating Token Index: 36

Text #18

Max Range: 1.7372. Min Range: -1.7372

Max Act: 0.9109. Min Act: -0.0000

Data Index: 324368 (The Pile)

Max Activating Token Index: 797

Text #19

Max Range: 1.7372. Min Range: -1.7372

Max Act: 0.9977. Min Act: -0.0000

Data Index: 1486619 (The Pile)

Max Activating Token Index: 402