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

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

Neuron 474 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: 5.6539. Min Range: -5.6539

Max Act: 5.6539. Min Act: -0.1700

Data Index: 735669 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 5.6539. Min Range: -5.6539

Max Act: 5.4352. Min Act: -0.1700

Data Index: 974711 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 5.6539. Min Range: -5.6539

Max Act: 5.4664. Min Act: -0.1700

Data Index: 870511 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 5.6539. Min Range: -5.6539

Max Act: 5.3102. Min Act: -0.1700

Data Index: 637462 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 5.6539. Min Range: -5.6539

Max Act: 5.3102. Min Act: -0.1700

Data Index: 313104 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 5.6539. Min Range: -5.6539

Max Act: 5.2477. Min Act: -0.1700

Data Index: 23722 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 5.6539. Min Range: -5.6539

Max Act: 5.2789. Min Act: -0.1700

Data Index: 1046132 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 5.6539. Min Range: -5.6539

Max Act: 5.2477. Min Act: -0.1700

Data Index: 922331 (C4 (Web Text))

Max Activating Token Index: 363

Text #8

Max Range: 5.6539. Min Range: -5.6539

Max Act: 5.2477. Min Act: -0.1700

Data Index: 761039 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 5.6539. Min Range: -5.6539

Max Act: 5.1227. Min Act: -0.1700

Data Index: 33272 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 5.6539. Min Range: -5.6539

Max Act: 5.1539. Min Act: -0.1700

Data Index: 760697 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 5.6539. Min Range: -5.6539

Max Act: 5.1539. Min Act: -0.1700

Data Index: 449285 (C4 (Web Text))

Max Activating Token Index: 753

Text #12

Max Range: 5.6539. Min Range: -5.6539

Max Act: 5.1227. Min Act: -0.1700

Data Index: 484855 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 5.6539. Min Range: -5.6539

Max Act: 5.1227. Min Act: -0.1700

Data Index: 1340679 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 5.6539. Min Range: -5.6539

Max Act: 5.1227. Min Act: -0.1700

Data Index: 905847 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 5.6539. Min Range: -5.6539

Max Act: 5.0602. Min Act: -0.1700

Data Index: 137091 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 5.6539. Min Range: -5.6539

Max Act: 5.0914. Min Act: -0.1700

Data Index: 384311 (C4 (Web Text))

Max Activating Token Index: 462

Text #17

Max Range: 5.6539. Min Range: -5.6539

Max Act: 5.1227. Min Act: -0.1700

Data Index: 620962 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 5.6539. Min Range: -5.6539

Max Act: 4.9977. Min Act: -0.1700

Data Index: 764433 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 5.6539. Min Range: -5.6539

Max Act: 5.0914. Min Act: -0.1700

Data Index: 858309 (C4 (Web Text))

Max Activating Token Index: 688