Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1949 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1922. Min Range: -5.1922
Max Act: 5.1922. Min Act: -0.1700
Data Index: 3814507 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1922. Min Range: -5.1922
Max Act: 5.1297. Min Act: -0.1700
Data Index: 1151509 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1922. Min Range: -5.1922
Max Act: 5.1297. Min Act: -0.1700
Data Index: 2378289 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1922. Min Range: -5.1922
Max Act: 5.0672. Min Act: -0.1700
Data Index: 5869720 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1922. Min Range: -5.1922
Max Act: 5.0047. Min Act: -0.1700
Data Index: 4721653 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1922. Min Range: -5.1922
Max Act: 5.0359. Min Act: -0.1700
Data Index: 8737596 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1922. Min Range: -5.1922
Max Act: 5.0047. Min Act: -0.1700
Data Index: 6084188 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1922. Min Range: -5.1922
Max Act: 5.0047. Min Act: -0.1700
Data Index: 1556687 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1922. Min Range: -5.1922
Max Act: 4.9422. Min Act: -0.1700
Data Index: 8770548 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1922. Min Range: -5.1922
Max Act: 4.9422. Min Act: -0.1700
Data Index: 2334942 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1922. Min Range: -5.1922
Max Act: 4.9422. Min Act: -0.1700
Data Index: 866702 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1922. Min Range: -5.1922
Max Act: 4.9422. Min Act: -0.1700
Data Index: 3197772 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1922. Min Range: -5.1922
Max Act: 4.9109. Min Act: -0.1700
Data Index: 8250010 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1922. Min Range: -5.1922
Max Act: 4.9109. Min Act: -0.1700
Data Index: 4852944 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1922. Min Range: -5.1922
Max Act: 4.8484. Min Act: -0.1700
Data Index: 4484539 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1922. Min Range: -5.1922
Max Act: 4.8797. Min Act: -0.1700
Data Index: 7674047 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1922. Min Range: -5.1922
Max Act: 4.8797. Min Act: -0.1700
Data Index: 966857 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1922. Min Range: -5.1922
Max Act: 4.8797. Min Act: -0.1700
Data Index: 5644429 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1922. Min Range: -5.1922
Max Act: 4.8797. Min Act: -0.1700
Data Index: 5223819 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1922. Min Range: -5.1922
Max Act: 4.8797. Min Act: -0.1700
Data Index: 1271663 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19