Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2302 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.9387. Min Act: -0.0002

Data Index: 106655 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.8487. Min Act: -0.0003

Data Index: 1127528 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.8244. Min Act: -0.0002

Data Index: 326820 (C4 (Web Text))

Max Activating Token Index: 702

Text #3

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.8200. Min Act: -0.0002

Data Index: 567485 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.7972. Min Act: -0.0003

Data Index: 333046 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.8064. Min Act: -0.0002

Data Index: 183461 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.7840. Min Act: -0.0002

Data Index: 604910 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.7882. Min Act: -0.0002

Data Index: 751082 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.7839. Min Act: -0.0003

Data Index: 1264973 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.7789. Min Act: -0.0002

Data Index: 419587 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.7587. Min Act: -0.0002

Data Index: 848607 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.7568. Min Act: -0.0002

Data Index: 1185046 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.7436. Min Act: -0.0003

Data Index: 1096441 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.7503. Min Act: -0.0002

Data Index: 153917 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.7540. Min Act: -0.0002

Data Index: 764589 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.7478. Min Act: -0.0002

Data Index: 30411 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.7391. Min Act: -0.0003

Data Index: 818305 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.7458. Min Act: -0.0002

Data Index: 226512 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.7568. Min Act: -0.0002

Data Index: 247559 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.7312. Min Act: -0.0002

Data Index: 65428 (C4 (Web Text))

Max Activating Token Index: 240