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

Dataset: The Pile

Neuron 2088 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.3849. Min Act: -0.0000

Data Index: 1442491 (The Pile)

Max Activating Token Index: 808

Text #1

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.3452. Min Act: 0.0000

Data Index: 1631961 (The Pile)

Max Activating Token Index: 503

Text #2

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.3643. Min Act: -0.0000

Data Index: 1016250 (The Pile)

Max Activating Token Index: 731

Text #3

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.3580. Min Act: -0.0000

Data Index: 813267 (The Pile)

Max Activating Token Index: 434

Text #4

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.3672. Min Act: -0.0000

Data Index: 19380 (The Pile)

Max Activating Token Index: 198

Text #5

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.3788. Min Act: -0.0000

Data Index: 1422060 (The Pile)

Max Activating Token Index: 105

Text #6

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.3613. Min Act: -0.0000

Data Index: 350931 (The Pile)

Max Activating Token Index: 583

Text #7

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.3457. Min Act: -0.0000

Data Index: 640876 (The Pile)

Max Activating Token Index: 318

Text #8

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.3014. Min Act: -0.0000

Data Index: 1368636 (The Pile)

Max Activating Token Index: 507

Text #9

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.3375. Min Act: -0.0000

Data Index: 304968 (The Pile)

Max Activating Token Index: 164

Text #10

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.3141. Min Act: 0.0000

Data Index: 1471164 (The Pile)

Max Activating Token Index: 169

Text #11

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.3255. Min Act: 0.0000

Data Index: 557721 (The Pile)

Max Activating Token Index: 441

Text #12

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.3060. Min Act: -0.0000

Data Index: 1770339 (The Pile)

Max Activating Token Index: 199

Text #13

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.3278. Min Act: -0.0000

Data Index: 472199 (The Pile)

Max Activating Token Index: 1021

Text #14

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.3096. Min Act: -0.0000

Data Index: 858138 (The Pile)

Max Activating Token Index: 816

Text #15

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.3276. Min Act: -0.0000

Data Index: 432559 (The Pile)

Max Activating Token Index: 185

Text #16

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.3309. Min Act: -0.0000

Data Index: 1088908 (The Pile)

Max Activating Token Index: 746

Text #17

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.3233. Min Act: 0.0000

Data Index: 655861 (The Pile)

Max Activating Token Index: 768

Text #18

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2940. Min Act: -0.0000

Data Index: 683192 (The Pile)

Max Activating Token Index: 87

Text #19

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.3002. Min Act: -0.0000

Data Index: 1399786 (The Pile)

Max Activating Token Index: 637