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

Dataset: The Pile

Neuron 2112 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: 0.8117. Min Range: -0.8117

Max Act: 0.8117. Min Act: -0.0000

Data Index: 8525 (The Pile)

Max Activating Token Index: 873

Text #1

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.7778. Min Act: -0.0000

Data Index: 1532047 (The Pile)

Max Activating Token Index: 482

Text #2

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.7691. Min Act: -0.0000

Data Index: 1418484 (The Pile)

Max Activating Token Index: 65

Text #3

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.6631. Min Act: -0.0000

Data Index: 1837540 (The Pile)

Max Activating Token Index: 240

Text #4

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.6578. Min Act: -0.0000

Data Index: 1252186 (The Pile)

Max Activating Token Index: 318

Text #5

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.6319. Min Act: -0.0000

Data Index: 1156453 (The Pile)

Max Activating Token Index: 79

Text #6

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.6299. Min Act: -0.0000

Data Index: 1466711 (The Pile)

Max Activating Token Index: 702

Text #7

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.6171. Min Act: -0.0000

Data Index: 892660 (The Pile)

Max Activating Token Index: 594

Text #8

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.6259. Min Act: -0.0000

Data Index: 1348406 (The Pile)

Max Activating Token Index: 568

Text #9

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.6066. Min Act: -0.0000

Data Index: 118096 (The Pile)

Max Activating Token Index: 36

Text #10

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.6070. Min Act: -0.0000

Data Index: 1449781 (The Pile)

Max Activating Token Index: 290

Text #11

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.5646. Min Act: -0.0000

Data Index: 1277860 (The Pile)

Max Activating Token Index: 245

Text #12

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.5428. Min Act: -0.0000

Data Index: 1769078 (The Pile)

Max Activating Token Index: 208

Text #13

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.5618. Min Act: -0.0000

Data Index: 84279 (The Pile)

Max Activating Token Index: 567

Text #14

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.5988. Min Act: -0.0000

Data Index: 1760017 (The Pile)

Max Activating Token Index: 361

Text #15

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.4892. Min Act: -0.0000

Data Index: 1265464 (The Pile)

Max Activating Token Index: 118

Text #16

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.6188. Min Act: -0.0000

Data Index: 738078 (The Pile)

Max Activating Token Index: 924

Text #17

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.6084. Min Act: -0.0000

Data Index: 1406070 (The Pile)

Max Activating Token Index: 859

Text #18

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.5349. Min Act: -0.0000

Data Index: 464616 (The Pile)

Max Activating Token Index: 556

Text #19

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.5463. Min Act: -0.0000

Data Index: 1728378 (The Pile)

Max Activating Token Index: 919