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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3787 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1387. Min Range: -2.1387

Max Act: 2.1387. Min Act: -0.0000

Data Index: 723084 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 2.1387. Min Range: -2.1387

Max Act: 1.9453. Min Act: -0.0000

Data Index: 941624 (C4 (Web Text))

Max Activating Token Index: 1020

Text #2

Max Range: 2.1387. Min Range: -2.1387

Max Act: 1.8094. Min Act: -0.0000

Data Index: 1092255 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 2.1387. Min Range: -2.1387

Max Act: 1.8104. Min Act: -0.0000

Data Index: 295772 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 2.1387. Min Range: -2.1387

Max Act: 1.6736. Min Act: -0.0000

Data Index: 345131 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 2.1387. Min Range: -2.1387

Max Act: 1.6502. Min Act: -0.0000

Data Index: 70821 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 2.1387. Min Range: -2.1387

Max Act: 1.7932. Min Act: -0.0000

Data Index: 276153 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 2.1387. Min Range: -2.1387

Max Act: 1.6990. Min Act: -0.0000

Data Index: 476574 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 2.1387. Min Range: -2.1387

Max Act: 1.5906. Min Act: -0.0000

Data Index: 153257 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 2.1387. Min Range: -2.1387

Max Act: 1.6915. Min Act: -0.0000

Data Index: 98488 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 2.1387. Min Range: -2.1387

Max Act: 1.6739. Min Act: -0.0000

Data Index: 156370 (C4 (Web Text))

Max Activating Token Index: 1003

Text #11

Max Range: 2.1387. Min Range: -2.1387

Max Act: 1.6675. Min Act: -0.0000

Data Index: 1323296 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 2.1387. Min Range: -2.1387

Max Act: 1.6557. Min Act: -0.0000

Data Index: 923200 (C4 (Web Text))

Max Activating Token Index: 378

Text #13

Max Range: 2.1387. Min Range: -2.1387

Max Act: 1.5928. Min Act: -0.0000

Data Index: 198981 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 2.1387. Min Range: -2.1387

Max Act: 1.5849. Min Act: -0.0000

Data Index: 866337 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 2.1387. Min Range: -2.1387

Max Act: 1.5987. Min Act: -0.0000

Data Index: 612099 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 2.1387. Min Range: -2.1387

Max Act: 1.6818. Min Act: -0.0000

Data Index: 306332 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 2.1387. Min Range: -2.1387

Max Act: 1.6404. Min Act: -0.0000

Data Index: 592749 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 2.1387. Min Range: -2.1387

Max Act: 1.4621. Min Act: -0.0000

Data Index: 138504 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 2.1387. Min Range: -2.1387

Max Act: 1.5457. Min Act: -0.0000

Data Index: 141123 (C4 (Web Text))

Max Activating Token Index: 827