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

Dataset: The Pile

Neuron 2423 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.7387. Min Act: -0.0000

Data Index: 619607 (The Pile)

Max Activating Token Index: 68

Text #1

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6988. Min Act: -0.0000

Data Index: 396698 (The Pile)

Max Activating Token Index: 610

Text #2

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6718. Min Act: -0.0000

Data Index: 1540436 (The Pile)

Max Activating Token Index: 119

Text #3

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6925. Min Act: -0.0000

Data Index: 1658988 (The Pile)

Max Activating Token Index: 736

Text #4

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6689. Min Act: -0.0000

Data Index: 154195 (The Pile)

Max Activating Token Index: 947

Text #5

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6484. Min Act: -0.0000

Data Index: 775994 (The Pile)

Max Activating Token Index: 1006

Text #6

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6647. Min Act: -0.0000

Data Index: 1428838 (The Pile)

Max Activating Token Index: 544

Text #7

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6445. Min Act: -0.0000

Data Index: 118551 (The Pile)

Max Activating Token Index: 58

Text #8

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6547. Min Act: -0.0000

Data Index: 1965177 (The Pile)

Max Activating Token Index: 658

Text #9

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6519. Min Act: -0.0000

Data Index: 1392066 (The Pile)

Max Activating Token Index: 565

Text #10

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6465. Min Act: -0.0000

Data Index: 141253 (The Pile)

Max Activating Token Index: 964

Text #11

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6269. Min Act: -0.0000

Data Index: 50763 (The Pile)

Max Activating Token Index: 60

Text #12

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6434. Min Act: -0.0000

Data Index: 410061 (The Pile)

Max Activating Token Index: 1022

Text #13

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6248. Min Act: -0.0000

Data Index: 1658715 (The Pile)

Max Activating Token Index: 47

Text #14

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6548. Min Act: -0.0000

Data Index: 747006 (The Pile)

Max Activating Token Index: 851

Text #15

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6314. Min Act: -0.0000

Data Index: 223685 (The Pile)

Max Activating Token Index: 973

Text #16

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6361. Min Act: -0.0000

Data Index: 878055 (The Pile)

Max Activating Token Index: 152

Text #17

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6123. Min Act: -0.0000

Data Index: 1993057 (The Pile)

Max Activating Token Index: 94

Text #18

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6378. Min Act: -0.0000

Data Index: 1348387 (The Pile)

Max Activating Token Index: 112

Text #19

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6487. Min Act: -0.0000

Data Index: 1644406 (The Pile)

Max Activating Token Index: 621