Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4048 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7848. Min Range: -3.7848
Max Act: 3.7848. Min Act: -0.1700
Data Index: 7898052 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7848. Min Range: -3.7848
Max Act: 3.7223. Min Act: -0.1700
Data Index: 807034 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7848. Min Range: -3.7848
Max Act: 3.6910. Min Act: -0.1700
Data Index: 6546209 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7848. Min Range: -3.7848
Max Act: 3.6284. Min Act: -0.1700
Data Index: 8061218 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7848. Min Range: -3.7848
Max Act: 3.6284. Min Act: -0.1700
Data Index: 6765870 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7848. Min Range: -3.7848
Max Act: 3.5815. Min Act: -0.1700
Data Index: 7943844 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7848. Min Range: -3.7848
Max Act: 3.5815. Min Act: -0.1700
Data Index: 1892910 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7848. Min Range: -3.7848
Max Act: 3.5502. Min Act: -0.1700
Data Index: 5759982 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7848. Min Range: -3.7848
Max Act: 3.5032. Min Act: -0.1700
Data Index: 7067859 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7848. Min Range: -3.7848
Max Act: 3.5032. Min Act: -0.1700
Data Index: 583810 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7848. Min Range: -3.7848
Max Act: 3.5032. Min Act: -0.1700
Data Index: 4429219 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7848. Min Range: -3.7848
Max Act: 3.5188. Min Act: -0.1700
Data Index: 7887292 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7848. Min Range: -3.7848
Max Act: 3.4875. Min Act: -0.1700
Data Index: 6862684 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7848. Min Range: -3.7848
Max Act: 3.4875. Min Act: -0.1700
Data Index: 264782 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7848. Min Range: -3.7848
Max Act: 3.4875. Min Act: -0.1700
Data Index: 6160142 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7848. Min Range: -3.7848
Max Act: 3.4718. Min Act: -0.1700
Data Index: 2082011 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7848. Min Range: -3.7848
Max Act: 3.4562. Min Act: -0.1700
Data Index: 6019505 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7848. Min Range: -3.7848
Max Act: 3.4562. Min Act: -0.1700
Data Index: 2331271 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7848. Min Range: -3.7848
Max Act: 3.4248. Min Act: -0.1700
Data Index: 3381052 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7848. Min Range: -3.7848
Max Act: 3.3778. Min Act: -0.1700
Data Index: 252783 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #19