Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2056 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4126. Min Range: -7.4126
Max Act: 7.4126. Min Act: -0.1700
Data Index: 5464075 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4126. Min Range: -7.4126
Max Act: 7.0688. Min Act: -0.1700
Data Index: 3460172 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4126. Min Range: -7.4126
Max Act: 7.0063. Min Act: -0.1700
Data Index: 2371740 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4126. Min Range: -7.4126
Max Act: 7.0063. Min Act: -0.1700
Data Index: 5132776 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4126. Min Range: -7.4126
Max Act: 6.9438. Min Act: -0.1700
Data Index: 1389565 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4126. Min Range: -7.4126
Max Act: 6.9438. Min Act: -0.1700
Data Index: 6578 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4126. Min Range: -7.4126
Max Act: 6.9438. Min Act: -0.1700
Data Index: 8329859 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4126. Min Range: -7.4126
Max Act: 6.9438. Min Act: -0.1700
Data Index: 5892766 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4126. Min Range: -7.4126
Max Act: 6.9438. Min Act: -0.1700
Data Index: 4645324 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4126. Min Range: -7.4126
Max Act: 6.8813. Min Act: -0.1700
Data Index: 7284330 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4126. Min Range: -7.4126
Max Act: 6.8501. Min Act: -0.1700
Data Index: 3016505 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4126. Min Range: -7.4126
Max Act: 6.9126. Min Act: -0.1700
Data Index: 88329 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4126. Min Range: -7.4126
Max Act: 6.8501. Min Act: -0.1700
Data Index: 4035576 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4126. Min Range: -7.4126
Max Act: 6.8188. Min Act: -0.1700
Data Index: 840044 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4126. Min Range: -7.4126
Max Act: 6.7563. Min Act: -0.1700
Data Index: 681244 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4126. Min Range: -7.4126
Max Act: 6.7876. Min Act: -0.1700
Data Index: 5226454 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4126. Min Range: -7.4126
Max Act: 6.7251. Min Act: -0.1700
Data Index: 1141754 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4126. Min Range: -7.4126
Max Act: 6.7563. Min Act: -0.1700
Data Index: 5433720 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4126. Min Range: -7.4126
Max Act: 6.7251. Min Act: -0.1700
Data Index: 2396765 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4126. Min Range: -7.4126
Max Act: 6.6938. Min Act: -0.1700
Data Index: 4508828 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19