Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 989 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.5587. Min Range: -3.5587

Max Act: 3.5587. Min Act: -0.1700

Data Index: 1600334 (Python Code)

Max Activating Token Index: 498

Text #1

Max Range: 3.5587. Min Range: -3.5587

Max Act: 3.3863. Min Act: -0.1700

Data Index: 1474846 (Python Code)

Max Activating Token Index: 953

Text #2

Max Range: 3.5587. Min Range: -3.5587

Max Act: 3.3863. Min Act: -0.1700

Data Index: 1446315 (Python Code)

Max Activating Token Index: 111

Text #3

Max Range: 3.5587. Min Range: -3.5587

Max Act: 3.4020. Min Act: -0.1700

Data Index: 1473954 (Python Code)

Max Activating Token Index: 21

Text #4

Max Range: 3.5587. Min Range: -3.5587

Max Act: 3.2135. Min Act: -0.1700

Data Index: 1621838 (Python Code)

Max Activating Token Index: 3

Text #5

Max Range: 3.5587. Min Range: -3.5587

Max Act: 3.1978. Min Act: -0.1700

Data Index: 1548754 (Python Code)

Max Activating Token Index: 727

Text #6

Max Range: 3.5587. Min Range: -3.5587

Max Act: 3.1663. Min Act: -0.1700

Data Index: 1560784 (Python Code)

Max Activating Token Index: 995

Text #7

Max Range: 3.5587. Min Range: -3.5587

Max Act: 3.0718. Min Act: -0.1700

Data Index: 1642387 (Python Code)

Max Activating Token Index: 877

Text #8

Max Range: 3.5587. Min Range: -3.5587

Max Act: 3.0402. Min Act: -0.1700

Data Index: 1592426 (Python Code)

Max Activating Token Index: 196

Text #9

Max Range: 3.5587. Min Range: -3.5587

Max Act: 3.0244. Min Act: -0.1700

Data Index: 1441838 (Python Code)

Max Activating Token Index: 394

Text #10

Max Range: 3.5587. Min Range: -3.5587

Max Act: 3.0560. Min Act: -0.1700

Data Index: 1514910 (Python Code)

Max Activating Token Index: 113

Text #11

Max Range: 3.5587. Min Range: -3.5587

Max Act: 3.0402. Min Act: -0.1700

Data Index: 1616113 (Python Code)

Max Activating Token Index: 660

Text #12

Max Range: 3.5587. Min Range: -3.5587

Max Act: 3.0086. Min Act: -0.1700

Data Index: 1646194 (Python Code)

Max Activating Token Index: 696

Text #13

Max Range: 3.5587. Min Range: -3.5587

Max Act: 3.0244. Min Act: -0.1700

Data Index: 1434174 (Python Code)

Max Activating Token Index: 550

Text #14

Max Range: 3.5587. Min Range: -3.5587

Max Act: 2.9928. Min Act: -0.1700

Data Index: 1449960 (Python Code)

Max Activating Token Index: 476

Text #15

Max Range: 3.5587. Min Range: -3.5587

Max Act: 2.9770. Min Act: -0.1700

Data Index: 1544847 (Python Code)

Max Activating Token Index: 480

Text #16

Max Range: 3.5587. Min Range: -3.5587

Max Act: 2.9928. Min Act: -0.1700

Data Index: 1498930 (Python Code)

Max Activating Token Index: 268

Text #17

Max Range: 3.5587. Min Range: -3.5587

Max Act: 2.9612. Min Act: -0.1700

Data Index: 1645957 (Python Code)

Max Activating Token Index: 515

Text #18

Max Range: 3.5587. Min Range: -3.5587

Max Act: 2.9770. Min Act: -0.1700

Data Index: 1595599 (Python Code)

Max Activating Token Index: 362

Text #19

Max Range: 3.5587. Min Range: -3.5587

Max Act: 2.9612. Min Act: -0.1700

Data Index: 1410143 (Python Code)

Max Activating Token Index: 469