Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2810 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5184. Min Range: -8.5184
Max Act: 8.5184. Min Act: -0.1700
Data Index: 2339940 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5184. Min Range: -8.5184
Max Act: 8.1434. Min Act: -0.1700
Data Index: 6225663 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5184. Min Range: -8.5184
Max Act: 8.0809. Min Act: -0.1700
Data Index: 1794604 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5184. Min Range: -8.5184
Max Act: 8.0809. Min Act: -0.1700
Data Index: 8731484 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5184. Min Range: -8.5184
Max Act: 8.0809. Min Act: -0.1700
Data Index: 3697519 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5184. Min Range: -8.5184
Max Act: 8.0184. Min Act: -0.1700
Data Index: 531181 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5184. Min Range: -8.5184
Max Act: 7.9559. Min Act: -0.1700
Data Index: 5532242 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5184. Min Range: -8.5184
Max Act: 7.8934. Min Act: -0.1700
Data Index: 8400687 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5184. Min Range: -8.5184
Max Act: 7.8309. Min Act: -0.1700
Data Index: 3184226 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5184. Min Range: -8.5184
Max Act: 7.7684. Min Act: -0.1700
Data Index: 4132345 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5184. Min Range: -8.5184
Max Act: 7.8309. Min Act: -0.1700
Data Index: 8310647 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5184. Min Range: -8.5184
Max Act: 7.7684. Min Act: -0.1700
Data Index: 5375020 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5184. Min Range: -8.5184
Max Act: 7.7059. Min Act: -0.1700
Data Index: 5030274 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5184. Min Range: -8.5184
Max Act: 7.7059. Min Act: -0.1700
Data Index: 4510869 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5184. Min Range: -8.5184
Max Act: 7.7059. Min Act: -0.1700
Data Index: 6994966 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5184. Min Range: -8.5184
Max Act: 7.6434. Min Act: -0.1700
Data Index: 4858458 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5184. Min Range: -8.5184
Max Act: 7.6434. Min Act: -0.1700
Data Index: 730012 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5184. Min Range: -8.5184
Max Act: 7.6434. Min Act: -0.1700
Data Index: 5860952 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5184. Min Range: -8.5184
Max Act: 7.6434. Min Act: -0.1700
Data Index: 4645471 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5184. Min Range: -8.5184
Max Act: 7.5809. Min Act: -0.1700
Data Index: 4621481 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #19