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

Dataset: The Pile

Neuron 4524 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: 0.6387. Min Range: -0.6387

Max Act: 0.6358. Min Act: -0.0000

Data Index: 1578450 (The Pile)

Max Activating Token Index: 421

Text #1

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.6387. Min Act: -0.0000

Data Index: 1004585 (The Pile)

Max Activating Token Index: 216

Text #2

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.5944. Min Act: -0.0000

Data Index: 917518 (The Pile)

Max Activating Token Index: 381

Text #3

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.6353. Min Act: -0.0000

Data Index: 247164 (The Pile)

Max Activating Token Index: 729

Text #4

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.5928. Min Act: -0.0000

Data Index: 1480426 (The Pile)

Max Activating Token Index: 425

Text #5

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.5851. Min Act: -0.0000

Data Index: 778172 (The Pile)

Max Activating Token Index: 970

Text #6

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.5354. Min Act: -0.0000

Data Index: 1435683 (The Pile)

Max Activating Token Index: 82

Text #7

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.5427. Min Act: -0.0000

Data Index: 140555 (The Pile)

Max Activating Token Index: 973

Text #8

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.5209. Min Act: -0.0000

Data Index: 460283 (The Pile)

Max Activating Token Index: 818

Text #9

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.5432. Min Act: -0.0000

Data Index: 173925 (The Pile)

Max Activating Token Index: 302

Text #10

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.4820. Min Act: -0.0000

Data Index: 680648 (The Pile)

Max Activating Token Index: 211

Text #11

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.5125. Min Act: -0.0000

Data Index: 1557378 (The Pile)

Max Activating Token Index: 527

Text #12

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.5010. Min Act: -0.0000

Data Index: 1022067 (The Pile)

Max Activating Token Index: 547

Text #13

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.4651. Min Act: -0.0000

Data Index: 1183923 (The Pile)

Max Activating Token Index: 899

Text #14

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.4940. Min Act: -0.0000

Data Index: 21072 (The Pile)

Max Activating Token Index: 510

Text #15

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.5199. Min Act: -0.0000

Data Index: 1511734 (The Pile)

Max Activating Token Index: 602

Text #16

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.4940. Min Act: -0.0000

Data Index: 1450577 (The Pile)

Max Activating Token Index: 177

Text #17

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.4963. Min Act: -0.0000

Data Index: 731414 (The Pile)

Max Activating Token Index: 84

Text #18

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.4616. Min Act: -0.0000

Data Index: 532788 (The Pile)

Max Activating Token Index: 244

Text #19

Max Range: 0.6387. Min Range: -0.6387

Max Act: 0.4478. Min Act: -0.0000

Data Index: 1579070 (The Pile)

Max Activating Token Index: 440