Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4477 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1659. Min Range: -6.1659
Max Act: 6.1659. Min Act: -0.1700
Data Index: 8242745 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1659. Min Range: -6.1659
Max Act: 6.1659. Min Act: -0.1700
Data Index: 3754412 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1659. Min Range: -6.1659
Max Act: 6.0721. Min Act: -0.1700
Data Index: 1615067 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1659. Min Range: -6.1659
Max Act: 6.0721. Min Act: -0.1700
Data Index: 4028526 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1659. Min Range: -6.1659
Max Act: 6.0409. Min Act: -0.1700
Data Index: 4457931 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1659. Min Range: -6.1659
Max Act: 6.0409. Min Act: -0.1700
Data Index: 1742412 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1659. Min Range: -6.1659
Max Act: 6.0096. Min Act: -0.1700
Data Index: 1615069 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1659. Min Range: -6.1659
Max Act: 5.9784. Min Act: -0.1700
Data Index: 575195 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1659. Min Range: -6.1659
Max Act: 5.9784. Min Act: -0.1700
Data Index: 2644808 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1659. Min Range: -6.1659
Max Act: 5.9471. Min Act: -0.1700
Data Index: 6410727 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1659. Min Range: -6.1659
Max Act: 5.9784. Min Act: -0.1700
Data Index: 1375659 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1659. Min Range: -6.1659
Max Act: 5.9159. Min Act: -0.1700
Data Index: 8378535 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1659. Min Range: -6.1659
Max Act: 5.9159. Min Act: -0.1700
Data Index: 8384772 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1659. Min Range: -6.1659
Max Act: 5.8846. Min Act: -0.1700
Data Index: 3969535 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1659. Min Range: -6.1659
Max Act: 5.8846. Min Act: -0.1700
Data Index: 6081565 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1659. Min Range: -6.1659
Max Act: 5.8534. Min Act: -0.1700
Data Index: 4457058 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1659. Min Range: -6.1659
Max Act: 5.8534. Min Act: -0.1700
Data Index: 8774292 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1659. Min Range: -6.1659
Max Act: 5.8534. Min Act: -0.1700
Data Index: 241836 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1659. Min Range: -6.1659
Max Act: 5.7909. Min Act: -0.1700
Data Index: 1801472 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1659. Min Range: -6.1659
Max Act: 5.8221. Min Act: -0.1700
Data Index: 1888493 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19