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

Dataset: The Pile

Neuron 4654 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.9617. Min Act: -0.0000

Data Index: 226613 (The Pile)

Max Activating Token Index: 524

Text #1

Max Range: 1.0387. Min Range: -1.0387

Max Act: 1.0387. Min Act: -0.0000

Data Index: 872386 (The Pile)

Max Activating Token Index: 256

Text #2

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.9435. Min Act: -0.0000

Data Index: 1644774 (The Pile)

Max Activating Token Index: 219

Text #3

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.8989. Min Act: -0.0000

Data Index: 1130513 (The Pile)

Max Activating Token Index: 536

Text #4

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.8889. Min Act: -0.0000

Data Index: 1245688 (The Pile)

Max Activating Token Index: 585

Text #5

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.8188. Min Act: -0.0000

Data Index: 490440 (The Pile)

Max Activating Token Index: 312

Text #6

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.7705. Min Act: -0.0000

Data Index: 1228563 (The Pile)

Max Activating Token Index: 257

Text #7

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.7576. Min Act: -0.0000

Data Index: 1153848 (The Pile)

Max Activating Token Index: 592

Text #8

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.7247. Min Act: -0.0000

Data Index: 1386620 (The Pile)

Max Activating Token Index: 725

Text #9

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.7743. Min Act: -0.0000

Data Index: 1101938 (The Pile)

Max Activating Token Index: 842

Text #10

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.7410. Min Act: -0.0000

Data Index: 8109 (The Pile)

Max Activating Token Index: 944

Text #11

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.5161. Min Act: -0.0000

Data Index: 174304 (The Pile)

Max Activating Token Index: 820

Text #12

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.6965. Min Act: -0.0000

Data Index: 1022226 (The Pile)

Max Activating Token Index: 816

Text #13

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.6839. Min Act: -0.0000

Data Index: 1626263 (The Pile)

Max Activating Token Index: 373

Text #14

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.7569. Min Act: -0.0000

Data Index: 569856 (The Pile)

Max Activating Token Index: 433

Text #15

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.6336. Min Act: -0.0000

Data Index: 836304 (The Pile)

Max Activating Token Index: 572

Text #16

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.6783. Min Act: -0.0000

Data Index: 1750667 (The Pile)

Max Activating Token Index: 889

Text #17

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.5594. Min Act: -0.0000

Data Index: 1152065 (The Pile)

Max Activating Token Index: 976

Text #18

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.6268. Min Act: -0.0000

Data Index: 384174 (The Pile)

Max Activating Token Index: 531

Text #19

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.7049. Min Act: -0.0000

Data Index: 1685232 (The Pile)

Max Activating Token Index: 330