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

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

Neuron 1452 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: 3.6054. Min Range: -3.6054

Max Act: 3.6054. Min Act: -0.1700

Data Index: 1501113 (Python Code)

Max Activating Token Index: 342

Text #1

Max Range: 3.6054. Min Range: -3.6054

Max Act: 3.5114. Min Act: -0.1700

Data Index: 1498132 (Python Code)

Max Activating Token Index: 721

Text #2

Max Range: 3.6054. Min Range: -3.6054

Max Act: 3.5114. Min Act: -0.1700

Data Index: 1577495 (Python Code)

Max Activating Token Index: 711

Text #3

Max Range: 3.6054. Min Range: -3.6054

Max Act: 3.5114. Min Act: -0.1700

Data Index: 1649483 (Python Code)

Max Activating Token Index: 722

Text #4

Max Range: 3.6054. Min Range: -3.6054

Max Act: 3.5428. Min Act: -0.1700

Data Index: 1643933 (Python Code)

Max Activating Token Index: 547

Text #5

Max Range: 3.6054. Min Range: -3.6054

Max Act: 3.5114. Min Act: -0.1700

Data Index: 1386698 (Python Code)

Max Activating Token Index: 517

Text #6

Max Range: 3.6054. Min Range: -3.6054

Max Act: 3.5741. Min Act: -0.1700

Data Index: 1410824 (Python Code)

Max Activating Token Index: 680

Text #7

Max Range: 3.6054. Min Range: -3.6054

Max Act: 3.4801. Min Act: -0.1700

Data Index: 1409446 (Python Code)

Max Activating Token Index: 981

Text #8

Max Range: 3.6054. Min Range: -3.6054

Max Act: 3.5114. Min Act: -0.1700

Data Index: 1409771 (Python Code)

Max Activating Token Index: 784

Text #9

Max Range: 3.6054. Min Range: -3.6054

Max Act: 3.5114. Min Act: -0.1700

Data Index: 1558258 (Python Code)

Max Activating Token Index: 737

Text #10

Max Range: 3.6054. Min Range: -3.6054

Max Act: 3.4801. Min Act: -0.1700

Data Index: 1377150 (Python Code)

Max Activating Token Index: 549

Text #11

Max Range: 3.6054. Min Range: -3.6054

Max Act: 3.5114. Min Act: -0.1700

Data Index: 1384442 (Python Code)

Max Activating Token Index: 584

Text #12

Max Range: 3.6054. Min Range: -3.6054

Max Act: 3.4801. Min Act: -0.1700

Data Index: 1580475 (Python Code)

Max Activating Token Index: 760

Text #13

Max Range: 3.6054. Min Range: -3.6054

Max Act: 3.4801. Min Act: -0.1700

Data Index: 1407618 (Python Code)

Max Activating Token Index: 765

Text #14

Max Range: 3.6054. Min Range: -3.6054

Max Act: 3.5114. Min Act: -0.1700

Data Index: 1389019 (Python Code)

Max Activating Token Index: 721

Text #15

Max Range: 3.6054. Min Range: -3.6054

Max Act: 3.5114. Min Act: -0.1700

Data Index: 1592061 (Python Code)

Max Activating Token Index: 888

Text #16

Max Range: 3.6054. Min Range: -3.6054

Max Act: 3.5114. Min Act: -0.1700

Data Index: 1515736 (Python Code)

Max Activating Token Index: 615

Text #17

Max Range: 3.6054. Min Range: -3.6054

Max Act: 3.5114. Min Act: -0.1700

Data Index: 1391373 (Python Code)

Max Activating Token Index: 547

Text #18

Max Range: 3.6054. Min Range: -3.6054

Max Act: 3.4801. Min Act: -0.1700

Data Index: 1507223 (Python Code)

Max Activating Token Index: 635

Text #19

Max Range: 3.6054. Min Range: -3.6054

Max Act: 3.4487. Min Act: -0.1700

Data Index: 1391730 (Python Code)

Max Activating Token Index: 721