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

Dataset: The Pile

Neuron 1522 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.3387. Min Act: -0.0000

Data Index: 294821 (The Pile)

Max Activating Token Index: 388

Text #1

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.3218. Min Act: -0.0000

Data Index: 623387 (The Pile)

Max Activating Token Index: 625

Text #2

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2903. Min Act: -0.0000

Data Index: 973422 (The Pile)

Max Activating Token Index: 660

Text #3

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2731. Min Act: -0.0000

Data Index: 303209 (The Pile)

Max Activating Token Index: 299

Text #4

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2671. Min Act: -0.0000

Data Index: 788077 (The Pile)

Max Activating Token Index: 96

Text #5

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2820. Min Act: -0.0000

Data Index: 1041397 (The Pile)

Max Activating Token Index: 824

Text #6

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2648. Min Act: -0.0000

Data Index: 836039 (The Pile)

Max Activating Token Index: 919

Text #7

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2527. Min Act: -0.0000

Data Index: 228642 (The Pile)

Max Activating Token Index: 449

Text #8

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2590. Min Act: -0.0000

Data Index: 387306 (The Pile)

Max Activating Token Index: 387

Text #9

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2443. Min Act: -0.0000

Data Index: 796130 (The Pile)

Max Activating Token Index: 886

Text #10

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2487. Min Act: -0.0000

Data Index: 1692327 (The Pile)

Max Activating Token Index: 30

Text #11

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2307. Min Act: -0.0000

Data Index: 1739137 (The Pile)

Max Activating Token Index: 460

Text #12

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2302. Min Act: -0.0000

Data Index: 1654656 (The Pile)

Max Activating Token Index: 298

Text #13

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2348. Min Act: -0.0000

Data Index: 290331 (The Pile)

Max Activating Token Index: 285

Text #14

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2338. Min Act: -0.0000

Data Index: 262324 (The Pile)

Max Activating Token Index: 701

Text #15

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2332. Min Act: -0.0000

Data Index: 485857 (The Pile)

Max Activating Token Index: 498

Text #16

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2311. Min Act: -0.0000

Data Index: 762475 (The Pile)

Max Activating Token Index: 221

Text #17

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2397. Min Act: -0.0000

Data Index: 468105 (The Pile)

Max Activating Token Index: 120

Text #18

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2290. Min Act: -0.0000

Data Index: 699143 (The Pile)

Max Activating Token Index: 109

Text #19

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2299. Min Act: -0.0000

Data Index: 694782 (The Pile)

Max Activating Token Index: 460