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

Dataset: The Pile

Neuron 3982 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: 0.3387. Min Range: -0.3387

Max Act: 0.2951. Min Act: -0.0000

Data Index: 30982 (The Pile)

Max Activating Token Index: 651

Text #1

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.3387. Min Act: -0.0000

Data Index: 443056 (The Pile)

Max Activating Token Index: 672

Text #2

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2863. Min Act: -0.0000

Data Index: 543784 (The Pile)

Max Activating Token Index: 901

Text #3

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2882. Min Act: -0.0000

Data Index: 1080412 (The Pile)

Max Activating Token Index: 164

Text #4

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2704. Min Act: -0.0000

Data Index: 1685455 (The Pile)

Max Activating Token Index: 948

Text #5

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2645. Min Act: -0.0000

Data Index: 712297 (The Pile)

Max Activating Token Index: 967

Text #6

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2575. Min Act: -0.0000

Data Index: 1816070 (The Pile)

Max Activating Token Index: 714

Text #7

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2736. Min Act: -0.0000

Data Index: 1264575 (The Pile)

Max Activating Token Index: 279

Text #8

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2542. Min Act: -0.0000

Data Index: 712108 (The Pile)

Max Activating Token Index: 467

Text #9

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2418. Min Act: 0.0000

Data Index: 1658290 (The Pile)

Max Activating Token Index: 513

Text #10

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2468. Min Act: -0.0000

Data Index: 203165 (The Pile)

Max Activating Token Index: 42

Text #11

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2468. Min Act: -0.0000

Data Index: 1066861 (The Pile)

Max Activating Token Index: 855

Text #12

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2435. Min Act: -0.0000

Data Index: 462191 (The Pile)

Max Activating Token Index: 281

Text #13

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2256. Min Act: -0.0000

Data Index: 116995 (The Pile)

Max Activating Token Index: 799

Text #14

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2362. Min Act: -0.0000

Data Index: 1153411 (The Pile)

Max Activating Token Index: 195

Text #15

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2314. Min Act: -0.0000

Data Index: 374528 (The Pile)

Max Activating Token Index: 651

Text #16

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2338. Min Act: -0.0000

Data Index: 1903537 (The Pile)

Max Activating Token Index: 531

Text #17

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2397. Min Act: -0.0000

Data Index: 1036757 (The Pile)

Max Activating Token Index: 218

Text #18

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2372. Min Act: -0.0000

Data Index: 1770122 (The Pile)

Max Activating Token Index: 18

Text #19

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2342. Min Act: -0.0000

Data Index: 1137650 (The Pile)

Max Activating Token Index: 48