Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 978 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.3628. Min Range: -5.3628

Max Act: 5.3628. Min Act: -0.1700

Data Index: 1542884 (Python Code)

Max Activating Token Index: 981

Text #1

Max Range: 5.3628. Min Range: -5.3628

Max Act: 5.2846. Min Act: -0.1700

Data Index: 1389266 (Python Code)

Max Activating Token Index: 98

Text #2

Max Range: 5.3628. Min Range: -5.3628

Max Act: 5.3003. Min Act: -0.1700

Data Index: 1609424 (Python Code)

Max Activating Token Index: 869

Text #3

Max Range: 5.3628. Min Range: -5.3628

Max Act: 5.3003. Min Act: -0.1700

Data Index: 1563142 (Python Code)

Max Activating Token Index: 645

Text #4

Max Range: 5.3628. Min Range: -5.3628

Max Act: 5.2534. Min Act: -0.1700

Data Index: 1379439 (Python Code)

Max Activating Token Index: 387

Text #5

Max Range: 5.3628. Min Range: -5.3628

Max Act: 5.2534. Min Act: -0.1700

Data Index: 1630222 (Python Code)

Max Activating Token Index: 673

Text #6

Max Range: 5.3628. Min Range: -5.3628

Max Act: 5.2534. Min Act: -0.1700

Data Index: 1393070 (Python Code)

Max Activating Token Index: 974

Text #7

Max Range: 5.3628. Min Range: -5.3628

Max Act: 5.2690. Min Act: -0.1700

Data Index: 1416787 (Python Code)

Max Activating Token Index: 308

Text #8

Max Range: 5.3628. Min Range: -5.3628

Max Act: 5.2065. Min Act: -0.1700

Data Index: 1508719 (Python Code)

Max Activating Token Index: 520

Text #9

Max Range: 5.3628. Min Range: -5.3628

Max Act: 5.2690. Min Act: -0.1699

Data Index: 1469674 (Python Code)

Max Activating Token Index: 706

Text #10

Max Range: 5.3628. Min Range: -5.3628

Max Act: 5.2221. Min Act: -0.1700

Data Index: 1400292 (Python Code)

Max Activating Token Index: 724

Text #11

Max Range: 5.3628. Min Range: -5.3628

Max Act: 5.2065. Min Act: -0.1700

Data Index: 1577321 (Python Code)

Max Activating Token Index: 772

Text #12

Max Range: 5.3628. Min Range: -5.3628

Max Act: 5.2065. Min Act: -0.1699

Data Index: 1448267 (Python Code)

Max Activating Token Index: 597

Text #13

Max Range: 5.3628. Min Range: -5.3628

Max Act: 5.1909. Min Act: -0.1700

Data Index: 1555631 (Python Code)

Max Activating Token Index: 688

Text #14

Max Range: 5.3628. Min Range: -5.3628

Max Act: 5.2534. Min Act: -0.1700

Data Index: 1645256 (Python Code)

Max Activating Token Index: 1012

Text #15

Max Range: 5.3628. Min Range: -5.3628

Max Act: 5.2221. Min Act: -0.1700

Data Index: 1404491 (Python Code)

Max Activating Token Index: 805

Text #16

Max Range: 5.3628. Min Range: -5.3628

Max Act: 5.1440. Min Act: -0.1700

Data Index: 1558513 (Python Code)

Max Activating Token Index: 415

Text #17

Max Range: 5.3628. Min Range: -5.3628

Max Act: 5.1753. Min Act: -0.1700

Data Index: 1410649 (Python Code)

Max Activating Token Index: 940

Text #18

Max Range: 5.3628. Min Range: -5.3628

Max Act: 5.1753. Min Act: -0.1700

Data Index: 1463427 (Python Code)

Max Activating Token Index: 971

Text #19

Max Range: 5.3628. Min Range: -5.3628

Max Act: 5.1753. Min Act: -0.1699

Data Index: 1628535 (Python Code)

Max Activating Token Index: 509