Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 836 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.4387. Min Range: -4.4387

Max Act: 4.4387. Min Act: -0.1628

Data Index: 1423528 (Python Code)

Max Activating Token Index: 125

Text #1

Max Range: 4.4387. Min Range: -4.4387

Max Act: 4.3675. Min Act: -0.1655

Data Index: 1633403 (Python Code)

Max Activating Token Index: 111

Text #2

Max Range: 4.4387. Min Range: -4.4387

Max Act: 4.3501. Min Act: -0.1692

Data Index: 1605139 (Python Code)

Max Activating Token Index: 978

Text #3

Max Range: 4.4387. Min Range: -4.4387

Max Act: 4.2377. Min Act: -0.1587

Data Index: 1394591 (Python Code)

Max Activating Token Index: 571

Text #4

Max Range: 4.4387. Min Range: -4.4387

Max Act: 4.2126. Min Act: -0.1700

Data Index: 1571776 (Python Code)

Max Activating Token Index: 13

Text #5

Max Range: 4.4387. Min Range: -4.4387

Max Act: 4.2151. Min Act: -0.1473

Data Index: 1607035 (Python Code)

Max Activating Token Index: 39

Text #6

Max Range: 4.4387. Min Range: -4.4387

Max Act: 4.2008. Min Act: -0.1634

Data Index: 1610272 (Python Code)

Max Activating Token Index: 575

Text #7

Max Range: 4.4387. Min Range: -4.4387

Max Act: 4.1880. Min Act: -0.0196

Data Index: 1569700 (Python Code)

Max Activating Token Index: 77

Text #8

Max Range: 4.4387. Min Range: -4.4387

Max Act: 4.1661. Min Act: -0.0196

Data Index: 1566173 (Python Code)

Max Activating Token Index: 205

Text #9

Max Range: 4.4387. Min Range: -4.4387

Max Act: 4.1686. Min Act: -0.1694

Data Index: 1549870 (Python Code)

Max Activating Token Index: 501

Text #10

Max Range: 4.4387. Min Range: -4.4387

Max Act: 4.1576. Min Act: -0.1700

Data Index: 1522662 (Python Code)

Max Activating Token Index: 8

Text #11

Max Range: 4.4387. Min Range: -4.4387

Max Act: 4.1401. Min Act: -0.1640

Data Index: 1361852 (Python Code)

Max Activating Token Index: 63

Text #12

Max Range: 4.4387. Min Range: -4.4387

Max Act: 4.1191. Min Act: -0.1700

Data Index: 1447767 (Python Code)

Max Activating Token Index: 40

Text #13

Max Range: 4.4387. Min Range: -4.4387

Max Act: 4.1094. Min Act: -0.0196

Data Index: 1625551 (Python Code)

Max Activating Token Index: 718

Text #14

Max Range: 4.4387. Min Range: -4.4387

Max Act: 4.1120. Min Act: -0.1694

Data Index: 1548760 (Python Code)

Max Activating Token Index: 19

Text #15

Max Range: 4.4387. Min Range: -4.4387

Max Act: 4.0775. Min Act: -0.1700

Data Index: 1532565 (Python Code)

Max Activating Token Index: 209

Text #16

Max Range: 4.4387. Min Range: -4.4387

Max Act: 4.0742. Min Act: -0.1700

Data Index: 1598736 (Python Code)

Max Activating Token Index: 895

Text #17

Max Range: 4.4387. Min Range: -4.4387

Max Act: 4.0774. Min Act: -0.1700

Data Index: 1442894 (Python Code)

Max Activating Token Index: 9

Text #18

Max Range: 4.4387. Min Range: -4.4387

Max Act: 4.0748. Min Act: -0.1700

Data Index: 1432442 (Python Code)

Max Activating Token Index: 12

Text #19

Max Range: 4.4387. Min Range: -4.4387

Max Act: 4.0662. Min Act: -0.1688

Data Index: 1368116 (Python Code)

Max Activating Token Index: 10