Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1619 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 8.0387. Min Range: -8.0387

Max Act: 7.9762. Min Act: -0.1700

Data Index: 1617159 (Python Code)

Max Activating Token Index: 714

Text #1

Max Range: 8.0387. Min Range: -8.0387

Max Act: 8.0387. Min Act: -0.1700

Data Index: 1562710 (Python Code)

Max Activating Token Index: 500

Text #2

Max Range: 8.0387. Min Range: -8.0387

Max Act: 7.9450. Min Act: -0.1700

Data Index: 1462527 (Python Code)

Max Activating Token Index: 968

Text #3

Max Range: 8.0387. Min Range: -8.0387

Max Act: 7.7575. Min Act: -0.1700

Data Index: 1404638 (Python Code)

Max Activating Token Index: 888

Text #4

Max Range: 8.0387. Min Range: -8.0387

Max Act: 7.7262. Min Act: -0.1700

Data Index: 1505946 (Python Code)

Max Activating Token Index: 691

Text #5

Max Range: 8.0387. Min Range: -8.0387

Max Act: 7.5387. Min Act: -0.1700

Data Index: 1388315 (Python Code)

Max Activating Token Index: 703

Text #6

Max Range: 8.0387. Min Range: -8.0387

Max Act: 7.5700. Min Act: -0.1700

Data Index: 1615849 (Python Code)

Max Activating Token Index: 238

Text #7

Max Range: 8.0387. Min Range: -8.0387

Max Act: 7.4762. Min Act: -0.1700

Data Index: 1391304 (Python Code)

Max Activating Token Index: 174

Text #8

Max Range: 8.0387. Min Range: -8.0387

Max Act: 7.4450. Min Act: -0.1700

Data Index: 1440483 (Python Code)

Max Activating Token Index: 481

Text #9

Max Range: 8.0387. Min Range: -8.0387

Max Act: 7.5075. Min Act: -0.1700

Data Index: 1469405 (Python Code)

Max Activating Token Index: 826

Text #10

Max Range: 8.0387. Min Range: -8.0387

Max Act: 7.4450. Min Act: -0.1700

Data Index: 1618216 (Python Code)

Max Activating Token Index: 541

Text #11

Max Range: 8.0387. Min Range: -8.0387

Max Act: 7.4450. Min Act: -0.1700

Data Index: 1650270 (Python Code)

Max Activating Token Index: 163

Text #12

Max Range: 8.0387. Min Range: -8.0387

Max Act: 7.4137. Min Act: -0.1700

Data Index: 1599248 (Python Code)

Max Activating Token Index: 376

Text #13

Max Range: 8.0387. Min Range: -8.0387

Max Act: 7.3825. Min Act: -0.1700

Data Index: 1427723 (Python Code)

Max Activating Token Index: 320

Text #14

Max Range: 8.0387. Min Range: -8.0387

Max Act: 7.4137. Min Act: -0.1700

Data Index: 1525048 (Python Code)

Max Activating Token Index: 835

Text #15

Max Range: 8.0387. Min Range: -8.0387

Max Act: 7.4450. Min Act: -0.1700

Data Index: 1523351 (Python Code)

Max Activating Token Index: 589

Text #16

Max Range: 8.0387. Min Range: -8.0387

Max Act: 7.4137. Min Act: -0.1700

Data Index: 1396100 (Python Code)

Max Activating Token Index: 446

Text #17

Max Range: 8.0387. Min Range: -8.0387

Max Act: 7.4137. Min Act: -0.1700

Data Index: 1580133 (Python Code)

Max Activating Token Index: 812

Text #18

Max Range: 8.0387. Min Range: -8.0387

Max Act: 7.3825. Min Act: -0.1700

Data Index: 1433480 (Python Code)

Max Activating Token Index: 503

Text #19

Max Range: 8.0387. Min Range: -8.0387

Max Act: 7.3825. Min Act: -0.1700

Data Index: 1565631 (Python Code)

Max Activating Token Index: 514