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

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

Neuron 84 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: 3.3769. Min Range: -3.3769

Max Act: 3.3769. Min Act: -0.1700

Data Index: 1551099 (Python Code)

Max Activating Token Index: 780

Text #1

Max Range: 3.3769. Min Range: -3.3769

Max Act: 3.3298. Min Act: -0.1700

Data Index: 1641072 (Python Code)

Max Activating Token Index: 655

Text #2

Max Range: 3.3769. Min Range: -3.3769

Max Act: 3.3298. Min Act: -0.1700

Data Index: 1397187 (Python Code)

Max Activating Token Index: 22

Text #3

Max Range: 3.3769. Min Range: -3.3769

Max Act: 3.3141. Min Act: -0.1700

Data Index: 1423026 (Python Code)

Max Activating Token Index: 231

Text #4

Max Range: 3.3769. Min Range: -3.3769

Max Act: 3.3141. Min Act: -0.1700

Data Index: 1618196 (Python Code)

Max Activating Token Index: 719

Text #5

Max Range: 3.3769. Min Range: -3.3769

Max Act: 3.3141. Min Act: -0.1700

Data Index: 1468735 (Python Code)

Max Activating Token Index: 551

Text #6

Max Range: 3.3769. Min Range: -3.3769

Max Act: 3.3298. Min Act: -0.1700

Data Index: 1594148 (Python Code)

Max Activating Token Index: 889

Text #7

Max Range: 3.3769. Min Range: -3.3769

Max Act: 3.2984. Min Act: -0.1700

Data Index: 1468034 (Python Code)

Max Activating Token Index: 894

Text #8

Max Range: 3.3769. Min Range: -3.3769

Max Act: 3.2984. Min Act: -0.1700

Data Index: 1516335 (Python Code)

Max Activating Token Index: 615

Text #9

Max Range: 3.3769. Min Range: -3.3769

Max Act: 3.2670. Min Act: -0.1700

Data Index: 1546880 (Python Code)

Max Activating Token Index: 326

Text #10

Max Range: 3.3769. Min Range: -3.3769

Max Act: 3.2827. Min Act: -0.1700

Data Index: 1536028 (Python Code)

Max Activating Token Index: 529

Text #11

Max Range: 3.3769. Min Range: -3.3769

Max Act: 3.2670. Min Act: -0.1700

Data Index: 1545752 (Python Code)

Max Activating Token Index: 495

Text #12

Max Range: 3.3769. Min Range: -3.3769

Max Act: 3.2670. Min Act: -0.1700

Data Index: 1360306 (Python Code)

Max Activating Token Index: 718

Text #13

Max Range: 3.3769. Min Range: -3.3769

Max Act: 3.2670. Min Act: -0.1700

Data Index: 1556371 (Python Code)

Max Activating Token Index: 718

Text #14

Max Range: 3.3769. Min Range: -3.3769

Max Act: 3.2670. Min Act: -0.1700

Data Index: 1373378 (Python Code)

Max Activating Token Index: 718

Text #15

Max Range: 3.3769. Min Range: -3.3769

Max Act: 3.2355. Min Act: -0.1700

Data Index: 740913 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 3.3769. Min Range: -3.3769

Max Act: 3.2670. Min Act: -0.1700

Data Index: 986067 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 3.3769. Min Range: -3.3769

Max Act: 3.2827. Min Act: -0.1700

Data Index: 1603605 (Python Code)

Max Activating Token Index: 851

Text #18

Max Range: 3.3769. Min Range: -3.3769

Max Act: 3.2670. Min Act: -0.1700

Data Index: 1418243 (Python Code)

Max Activating Token Index: 516

Text #19

Max Range: 3.3769. Min Range: -3.3769

Max Act: 3.2670. Min Act: -0.1700

Data Index: 36879 (C4 (Web Text))

Max Activating Token Index: 427