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

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

Neuron 1595 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: 7.3679. Min Range: -7.3679

Max Act: 7.3679. Min Act: -0.1700

Data Index: 1093093 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 7.3679. Min Range: -7.3679

Max Act: 7.2741. Min Act: -0.1700

Data Index: 842309 (C4 (Web Text))

Max Activating Token Index: 689

Text #2

Max Range: 7.3679. Min Range: -7.3679

Max Act: 7.2116. Min Act: -0.1700

Data Index: 1101444 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 7.3679. Min Range: -7.3679

Max Act: 7.0554. Min Act: -0.1700

Data Index: 261574 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 7.3679. Min Range: -7.3679

Max Act: 6.8366. Min Act: -0.1700

Data Index: 634094 (C4 (Web Text))

Max Activating Token Index: 836

Text #5

Max Range: 7.3679. Min Range: -7.3679

Max Act: 6.8679. Min Act: -0.1700

Data Index: 487563 (C4 (Web Text))

Max Activating Token Index: 577

Text #6

Max Range: 7.3679. Min Range: -7.3679

Max Act: 6.8054. Min Act: -0.1700

Data Index: 765802 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 7.3679. Min Range: -7.3679

Max Act: 6.8679. Min Act: -0.1700

Data Index: 884468 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 7.3679. Min Range: -7.3679

Max Act: 6.8054. Min Act: -0.1700

Data Index: 542492 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 7.3679. Min Range: -7.3679

Max Act: 6.8054. Min Act: -0.1700

Data Index: 256581 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 7.3679. Min Range: -7.3679

Max Act: 6.7429. Min Act: -0.1700

Data Index: 127752 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 7.3679. Min Range: -7.3679

Max Act: 6.8366. Min Act: -0.1700

Data Index: 1088539 (C4 (Web Text))

Max Activating Token Index: 396

Text #12

Max Range: 7.3679. Min Range: -7.3679

Max Act: 6.7116. Min Act: -0.1700

Data Index: 650799 (C4 (Web Text))

Max Activating Token Index: 991

Text #13

Max Range: 7.3679. Min Range: -7.3679

Max Act: 6.7116. Min Act: -0.1694

Data Index: 1238301 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 7.3679. Min Range: -7.3679

Max Act: 6.7429. Min Act: -0.1700

Data Index: 201913 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 7.3679. Min Range: -7.3679

Max Act: 6.6804. Min Act: -0.1700

Data Index: 730093 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 7.3679. Min Range: -7.3679

Max Act: 6.7116. Min Act: -0.1700

Data Index: 256688 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 7.3679. Min Range: -7.3679

Max Act: 6.7116. Min Act: -0.1700

Data Index: 1250957 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 7.3679. Min Range: -7.3679

Max Act: 6.6804. Min Act: -0.1700

Data Index: 368421 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 7.3679. Min Range: -7.3679

Max Act: 6.6491. Min Act: -0.1699

Data Index: 856372 (C4 (Web Text))

Max Activating Token Index: 647