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

Dataset: The Pile

Neuron 1544 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3306. Min Range: -1.3306

Max Act: 1.3306. Min Act: -0.0000

Data Index: 1850393 (The Pile)

Max Activating Token Index: 883

Text #1

Max Range: 1.3306. Min Range: -1.3306

Max Act: 1.1808. Min Act: -0.0000

Data Index: 1510937 (The Pile)

Max Activating Token Index: 862

Text #2

Max Range: 1.3306. Min Range: -1.3306

Max Act: 1.1707. Min Act: -0.0000

Data Index: 1001045 (The Pile)

Max Activating Token Index: 503

Text #3

Max Range: 1.3306. Min Range: -1.3306

Max Act: 1.0882. Min Act: -0.0000

Data Index: 1404304 (The Pile)

Max Activating Token Index: 77

Text #4

Max Range: 1.3306. Min Range: -1.3306

Max Act: 1.1237. Min Act: -0.0000

Data Index: 500427 (The Pile)

Max Activating Token Index: 576

Text #5

Max Range: 1.3306. Min Range: -1.3306

Max Act: 1.1059. Min Act: -0.0000

Data Index: 356781 (The Pile)

Max Activating Token Index: 486

Text #6

Max Range: 1.3306. Min Range: -1.3306

Max Act: 1.0010. Min Act: -0.0000

Data Index: 39267 (The Pile)

Max Activating Token Index: 545

Text #7

Max Range: 1.3306. Min Range: -1.3306

Max Act: 0.9952. Min Act: -0.0001

Data Index: 776814 (The Pile)

Max Activating Token Index: 53

Text #8

Max Range: 1.3306. Min Range: -1.3306

Max Act: 0.9955. Min Act: -0.0000

Data Index: 1621956 (The Pile)

Max Activating Token Index: 275

Text #9

Max Range: 1.3306. Min Range: -1.3306

Max Act: 1.0807. Min Act: -0.0000

Data Index: 1340686 (The Pile)

Max Activating Token Index: 718

Text #10

Max Range: 1.3306. Min Range: -1.3306

Max Act: 0.9975. Min Act: -0.0000

Data Index: 1384876 (The Pile)

Max Activating Token Index: 143

Text #11

Max Range: 1.3306. Min Range: -1.3306

Max Act: 0.9775. Min Act: -0.0001

Data Index: 425313 (The Pile)

Max Activating Token Index: 149

Text #12

Max Range: 1.3306. Min Range: -1.3306

Max Act: 1.0040. Min Act: -0.0000

Data Index: 694407 (The Pile)

Max Activating Token Index: 660

Text #13

Max Range: 1.3306. Min Range: -1.3306

Max Act: 0.9608. Min Act: -0.0001

Data Index: 272761 (The Pile)

Max Activating Token Index: 433

Text #14

Max Range: 1.3306. Min Range: -1.3306

Max Act: 0.9744. Min Act: -0.0001

Data Index: 1176494 (The Pile)

Max Activating Token Index: 335

Text #15

Max Range: 1.3306. Min Range: -1.3306

Max Act: 0.9826. Min Act: -0.0000

Data Index: 155139 (The Pile)

Max Activating Token Index: 662

Text #16

Max Range: 1.3306. Min Range: -1.3306

Max Act: 0.9519. Min Act: -0.0000

Data Index: 360572 (The Pile)

Max Activating Token Index: 621

Text #17

Max Range: 1.3306. Min Range: -1.3306

Max Act: 0.9500. Min Act: -0.0000

Data Index: 1128259 (The Pile)

Max Activating Token Index: 314

Text #18

Max Range: 1.3306. Min Range: -1.3306

Max Act: 0.9434. Min Act: -0.0001

Data Index: 3107 (The Pile)

Max Activating Token Index: 130

Text #19

Max Range: 1.3306. Min Range: -1.3306

Max Act: 0.9757. Min Act: -0.0000

Data Index: 1784507 (The Pile)

Max Activating Token Index: 491