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

Dataset: The Pile

Neuron 3749 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.3830. Min Act: -0.0000

Data Index: 1790560 (The Pile)

Max Activating Token Index: 66

Text #1

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.1090. Min Act: -0.0000

Data Index: 1346940 (The Pile)

Max Activating Token Index: 446

Text #2

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.0387. Min Act: -0.0000

Data Index: 1789905 (The Pile)

Max Activating Token Index: 510

Text #3

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.0065. Min Act: 0.0001

Data Index: 1525469 (The Pile)

Max Activating Token Index: 289

Text #4

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.0980. Min Act: -0.0000

Data Index: 528052 (The Pile)

Max Activating Token Index: 991

Text #5

Max Range: 1.3830. Min Range: -1.3830

Max Act: 0.9016. Min Act: -0.0000

Data Index: 1116525 (The Pile)

Max Activating Token Index: 517

Text #6

Max Range: 1.3830. Min Range: -1.3830

Max Act: 0.9118. Min Act: -0.0000

Data Index: 1885041 (The Pile)

Max Activating Token Index: 457

Text #7

Max Range: 1.3830. Min Range: -1.3830

Max Act: 0.8776. Min Act: -0.0000

Data Index: 267348 (The Pile)

Max Activating Token Index: 321

Text #8

Max Range: 1.3830. Min Range: -1.3830

Max Act: 0.8236. Min Act: -0.0000

Data Index: 590980 (The Pile)

Max Activating Token Index: 446

Text #9

Max Range: 1.3830. Min Range: -1.3830

Max Act: 0.7760. Min Act: -0.0000

Data Index: 360864 (The Pile)

Max Activating Token Index: 225

Text #10

Max Range: 1.3830. Min Range: -1.3830

Max Act: 0.8633. Min Act: -0.0000

Data Index: 696617 (The Pile)

Max Activating Token Index: 376

Text #11

Max Range: 1.3830. Min Range: -1.3830

Max Act: 0.9214. Min Act: -0.0000

Data Index: 1949394 (The Pile)

Max Activating Token Index: 1022

Text #12

Max Range: 1.3830. Min Range: -1.3830

Max Act: 0.8360. Min Act: -0.0000

Data Index: 1381437 (The Pile)

Max Activating Token Index: 961

Text #13

Max Range: 1.3830. Min Range: -1.3830

Max Act: 0.8465. Min Act: -0.0000

Data Index: 1158275 (The Pile)

Max Activating Token Index: 503

Text #14

Max Range: 1.3830. Min Range: -1.3830

Max Act: 0.8392. Min Act: -0.0000

Data Index: 224388 (The Pile)

Max Activating Token Index: 793

Text #15

Max Range: 1.3830. Min Range: -1.3830

Max Act: 0.8266. Min Act: -0.0000

Data Index: 224570 (The Pile)

Max Activating Token Index: 544

Text #16

Max Range: 1.3830. Min Range: -1.3830

Max Act: 0.7960. Min Act: -0.0000

Data Index: 129358 (The Pile)

Max Activating Token Index: 225

Text #17

Max Range: 1.3830. Min Range: -1.3830

Max Act: 0.7757. Min Act: -0.0000

Data Index: 108181 (The Pile)

Max Activating Token Index: 373

Text #18

Max Range: 1.3830. Min Range: -1.3830

Max Act: 0.7583. Min Act: -0.0000

Data Index: 1941140 (The Pile)

Max Activating Token Index: 65

Text #19

Max Range: 1.3830. Min Range: -1.3830

Max Act: 0.7938. Min Act: -0.0000

Data Index: 666175 (The Pile)

Max Activating Token Index: 285