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

Dataset: The Pile

Neuron 4960 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: 0.7387. Min Range: -0.7387

Max Act: 0.7335. Min Act: -0.0000

Data Index: 347931 (The Pile)

Max Activating Token Index: 715

Text #1

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6821. Min Act: -0.0000

Data Index: 1162723 (The Pile)

Max Activating Token Index: 413

Text #2

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6684. Min Act: -0.0000

Data Index: 1554176 (The Pile)

Max Activating Token Index: 840

Text #3

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.7387. Min Act: -0.0000

Data Index: 612862 (The Pile)

Max Activating Token Index: 983

Text #4

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6380. Min Act: -0.0000

Data Index: 1441738 (The Pile)

Max Activating Token Index: 412

Text #5

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6281. Min Act: -0.0000

Data Index: 1130968 (The Pile)

Max Activating Token Index: 761

Text #6

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.5506. Min Act: -0.0000

Data Index: 19807 (The Pile)

Max Activating Token Index: 840

Text #7

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.5825. Min Act: -0.0000

Data Index: 1694683 (The Pile)

Max Activating Token Index: 536

Text #8

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.5992. Min Act: -0.0000

Data Index: 308821 (The Pile)

Max Activating Token Index: 671

Text #9

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.5982. Min Act: -0.0000

Data Index: 602690 (The Pile)

Max Activating Token Index: 264

Text #10

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6067. Min Act: -0.0000

Data Index: 604069 (The Pile)

Max Activating Token Index: 546

Text #11

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.5477. Min Act: -0.0000

Data Index: 65258 (The Pile)

Max Activating Token Index: 27

Text #12

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.5302. Min Act: -0.0000

Data Index: 538111 (The Pile)

Max Activating Token Index: 849

Text #13

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.5855. Min Act: -0.0000

Data Index: 285214 (The Pile)

Max Activating Token Index: 447

Text #14

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.5170. Min Act: -0.0000

Data Index: 695555 (The Pile)

Max Activating Token Index: 846

Text #15

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.5101. Min Act: -0.0000

Data Index: 1500516 (The Pile)

Max Activating Token Index: 477

Text #16

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.4968. Min Act: -0.0000

Data Index: 1900198 (The Pile)

Max Activating Token Index: 186

Text #17

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.5713. Min Act: -0.0000

Data Index: 1730528 (The Pile)

Max Activating Token Index: 519

Text #18

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.6008. Min Act: -0.0000

Data Index: 1562832 (The Pile)

Max Activating Token Index: 886

Text #19

Max Range: 0.7387. Min Range: -0.7387

Max Act: 0.4862. Min Act: -0.0000

Data Index: 1852491 (The Pile)

Max Activating Token Index: 557