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

Dataset: The Pile

Neuron 1875 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: 0.4502. Min Range: -0.4502

Max Act: 0.3813. Min Act: -0.0000

Data Index: 62859 (The Pile)

Max Activating Token Index: 650

Text #1

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.4431. Min Act: -0.0000

Data Index: 1594914 (The Pile)

Max Activating Token Index: 457

Text #2

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.4363. Min Act: -0.0000

Data Index: 1783180 (The Pile)

Max Activating Token Index: 533

Text #3

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.4289. Min Act: -0.0000

Data Index: 1390942 (The Pile)

Max Activating Token Index: 40

Text #4

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.4398. Min Act: -0.0000

Data Index: 47063 (The Pile)

Max Activating Token Index: 176

Text #5

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.4220. Min Act: -0.0000

Data Index: 1568843 (The Pile)

Max Activating Token Index: 296

Text #6

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.4216. Min Act: -0.0000

Data Index: 572736 (The Pile)

Max Activating Token Index: 839

Text #7

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.4321. Min Act: -0.0000

Data Index: 831154 (The Pile)

Max Activating Token Index: 340

Text #8

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.4129. Min Act: -0.0000

Data Index: 1304439 (The Pile)

Max Activating Token Index: 198

Text #9

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.4502. Min Act: 0.0000

Data Index: 1970664 (The Pile)

Max Activating Token Index: 116

Text #10

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.4305. Min Act: -0.0000

Data Index: 592863 (The Pile)

Max Activating Token Index: 50

Text #11

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3838. Min Act: -0.0000

Data Index: 1821161 (The Pile)

Max Activating Token Index: 713

Text #12

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3920. Min Act: -0.0000

Data Index: 1963086 (The Pile)

Max Activating Token Index: 613

Text #13

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3883. Min Act: -0.0000

Data Index: 1584472 (The Pile)

Max Activating Token Index: 367

Text #14

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.4004. Min Act: -0.0000

Data Index: 1213752 (The Pile)

Max Activating Token Index: 471

Text #15

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3650. Min Act: -0.0000

Data Index: 1750286 (The Pile)

Max Activating Token Index: 586

Text #16

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3895. Min Act: -0.0000

Data Index: 1443274 (The Pile)

Max Activating Token Index: 488

Text #17

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3596. Min Act: -0.0000

Data Index: 275536 (The Pile)

Max Activating Token Index: 736

Text #18

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3968. Min Act: -0.0000

Data Index: 934884 (The Pile)

Max Activating Token Index: 475

Text #19

Max Range: 0.4502. Min Range: -0.4502

Max Act: 0.3909. Min Act: -0.0000

Data Index: 312828 (The Pile)

Max Activating Token Index: 199