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

Dataset: The Pile

Neuron 1264 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: 1.9159. Min Range: -1.9159

Max Act: 1.9159. Min Act: -0.0000

Data Index: 1392327 (The Pile)

Max Activating Token Index: 289

Text #1

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.6169. Min Act: -0.0000

Data Index: 1005618 (The Pile)

Max Activating Token Index: 407

Text #2

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.7519. Min Act: -0.0000

Data Index: 890880 (The Pile)

Max Activating Token Index: 813

Text #3

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.6460. Min Act: -0.0000

Data Index: 596499 (The Pile)

Max Activating Token Index: 866

Text #4

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.5886. Min Act: -0.0000

Data Index: 401118 (The Pile)

Max Activating Token Index: 454

Text #5

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.5573. Min Act: -0.0000

Data Index: 1366772 (The Pile)

Max Activating Token Index: 222

Text #6

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.4375. Min Act: -0.0000

Data Index: 1143674 (The Pile)

Max Activating Token Index: 723

Text #7

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.6856. Min Act: -0.0000

Data Index: 1238738 (The Pile)

Max Activating Token Index: 591

Text #8

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.5482. Min Act: -0.0000

Data Index: 348630 (The Pile)

Max Activating Token Index: 149

Text #9

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.4571. Min Act: -0.0000

Data Index: 939376 (The Pile)

Max Activating Token Index: 339

Text #10

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.3704. Min Act: -0.0000

Data Index: 1320772 (The Pile)

Max Activating Token Index: 252

Text #11

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.4403. Min Act: -0.0000

Data Index: 1650328 (The Pile)

Max Activating Token Index: 493

Text #12

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.6076. Min Act: -0.0000

Data Index: 649860 (The Pile)

Max Activating Token Index: 923

Text #13

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.4147. Min Act: -0.0000

Data Index: 1195122 (The Pile)

Max Activating Token Index: 710

Text #14

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.5129. Min Act: -0.0000

Data Index: 507408 (The Pile)

Max Activating Token Index: 825

Text #15

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.3137. Min Act: -0.0000

Data Index: 1644017 (The Pile)

Max Activating Token Index: 383

Text #16

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.3683. Min Act: -0.0000

Data Index: 306972 (The Pile)

Max Activating Token Index: 411

Text #17

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.3677. Min Act: -0.0000

Data Index: 1368320 (The Pile)

Max Activating Token Index: 992

Text #18

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.3611. Min Act: -0.0000

Data Index: 1480527 (The Pile)

Max Activating Token Index: 236

Text #19

Max Range: 1.9159. Min Range: -1.9159

Max Act: 1.4305. Min Act: -0.0000

Data Index: 840682 (The Pile)

Max Activating Token Index: 591