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

Dataset: The Pile

Neuron 2395 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.4387. Min Act: -0.0000

Data Index: 1801269 (The Pile)

Max Activating Token Index: 510

Text #1

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.4266. Min Act: -0.0000

Data Index: 1062554 (The Pile)

Max Activating Token Index: 468

Text #2

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3745. Min Act: -0.0000

Data Index: 1421858 (The Pile)

Max Activating Token Index: 97

Text #3

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3604. Min Act: -0.0000

Data Index: 283316 (The Pile)

Max Activating Token Index: 538

Text #4

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3897. Min Act: -0.0000

Data Index: 37598 (The Pile)

Max Activating Token Index: 429

Text #5

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3622. Min Act: -0.0000

Data Index: 1405085 (The Pile)

Max Activating Token Index: 409

Text #6

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3541. Min Act: -0.0000

Data Index: 360691 (The Pile)

Max Activating Token Index: 277

Text #7

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3278. Min Act: -0.0000

Data Index: 1599268 (The Pile)

Max Activating Token Index: 832

Text #8

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3765. Min Act: -0.0000

Data Index: 272489 (The Pile)

Max Activating Token Index: 806

Text #9

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3471. Min Act: -0.0000

Data Index: 1847883 (The Pile)

Max Activating Token Index: 588

Text #10

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3168. Min Act: -0.0000

Data Index: 510622 (The Pile)

Max Activating Token Index: 35

Text #11

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3126. Min Act: -0.0000

Data Index: 1589552 (The Pile)

Max Activating Token Index: 679

Text #12

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2838. Min Act: -0.0000

Data Index: 16285 (The Pile)

Max Activating Token Index: 15

Text #13

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2722. Min Act: -0.0000

Data Index: 1306388 (The Pile)

Max Activating Token Index: 21

Text #14

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2896. Min Act: -0.0000

Data Index: 830918 (The Pile)

Max Activating Token Index: 221

Text #15

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2258. Min Act: -0.0000

Data Index: 1362161 (The Pile)

Max Activating Token Index: 836

Text #16

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2614. Min Act: -0.0000

Data Index: 1205034 (The Pile)

Max Activating Token Index: 471

Text #17

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2433. Min Act: -0.0000

Data Index: 398446 (The Pile)

Max Activating Token Index: 960

Text #18

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2215. Min Act: -0.0000

Data Index: 1362935 (The Pile)

Max Activating Token Index: 528

Text #19

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2506. Min Act: -0.0000

Data Index: 1156343 (The Pile)

Max Activating Token Index: 915