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

Dataset: The Pile

Neuron 1307 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: 1.0387. Min Range: -1.0387

Max Act: 1.0387. Min Act: -0.0000

Data Index: 731473 (The Pile)

Max Activating Token Index: 874

Text #1

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.9410. Min Act: -0.0000

Data Index: 1295490 (The Pile)

Max Activating Token Index: 566

Text #2

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.9095. Min Act: -0.0000

Data Index: 1335487 (The Pile)

Max Activating Token Index: 595

Text #3

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.9289. Min Act: -0.0000

Data Index: 1248570 (The Pile)

Max Activating Token Index: 300

Text #4

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.7930. Min Act: -0.0000

Data Index: 1792776 (The Pile)

Max Activating Token Index: 505

Text #5

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.8125. Min Act: -0.0000

Data Index: 1966098 (The Pile)

Max Activating Token Index: 389

Text #6

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.6939. Min Act: -0.0000

Data Index: 1415971 (The Pile)

Max Activating Token Index: 129

Text #7

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.7706. Min Act: -0.0000

Data Index: 188815 (The Pile)

Max Activating Token Index: 521

Text #8

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.7634. Min Act: -0.0000

Data Index: 1891978 (The Pile)

Max Activating Token Index: 197

Text #9

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.7185. Min Act: -0.0000

Data Index: 1047507 (The Pile)

Max Activating Token Index: 339

Text #10

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.7016. Min Act: -0.0000

Data Index: 1442143 (The Pile)

Max Activating Token Index: 92

Text #11

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.7669. Min Act: -0.0000

Data Index: 596333 (The Pile)

Max Activating Token Index: 492

Text #12

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.7379. Min Act: -0.0000

Data Index: 1583082 (The Pile)

Max Activating Token Index: 139

Text #13

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.8891. Min Act: -0.0000

Data Index: 67410 (The Pile)

Max Activating Token Index: 88

Text #14

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.6687. Min Act: -0.0000

Data Index: 640196 (The Pile)

Max Activating Token Index: 99

Text #15

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.6897. Min Act: -0.0000

Data Index: 1013700 (The Pile)

Max Activating Token Index: 562

Text #16

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.7327. Min Act: -0.0000

Data Index: 672913 (The Pile)

Max Activating Token Index: 390

Text #17

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.7106. Min Act: -0.0000

Data Index: 577636 (The Pile)

Max Activating Token Index: 259

Text #18

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.6198. Min Act: -0.0000

Data Index: 435900 (The Pile)

Max Activating Token Index: 196

Text #19

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.7266. Min Act: -0.0000

Data Index: 872594 (The Pile)

Max Activating Token Index: 94