Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 790 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4812. Min Range: -6.4812
Max Act: 6.4812. Min Act: -0.1700
Data Index: 6366932 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4812. Min Range: -6.4812
Max Act: 6.3562. Min Act: -0.1700
Data Index: 2958604 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4812. Min Range: -6.4812
Max Act: 6.0750. Min Act: -0.1700
Data Index: 2166918 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4812. Min Range: -6.4812
Max Act: 5.9812. Min Act: -0.1700
Data Index: 4544286 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4812. Min Range: -6.4812
Max Act: 5.7625. Min Act: -0.1700
Data Index: 1110706 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4812. Min Range: -6.4812
Max Act: 5.7625. Min Act: -0.1700
Data Index: 7591820 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4812. Min Range: -6.4812
Max Act: 5.7625. Min Act: -0.1700
Data Index: 1916857 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4812. Min Range: -6.4812
Max Act: 5.7000. Min Act: -0.1700
Data Index: 6651941 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4812. Min Range: -6.4812
Max Act: 5.6687. Min Act: -0.1700
Data Index: 6156639 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4812. Min Range: -6.4812
Max Act: 5.6687. Min Act: -0.1700
Data Index: 7735040 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4812. Min Range: -6.4812
Max Act: 5.6375. Min Act: -0.1700
Data Index: 2323849 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4812. Min Range: -6.4812
Max Act: 5.6062. Min Act: -0.1700
Data Index: 932693 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4812. Min Range: -6.4812
Max Act: 5.6062. Min Act: -0.1700
Data Index: 6296773 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4812. Min Range: -6.4812
Max Act: 5.5750. Min Act: -0.1700
Data Index: 5060912 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4812. Min Range: -6.4812
Max Act: 5.5750. Min Act: -0.1700
Data Index: 6091964 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4812. Min Range: -6.4812
Max Act: 5.5750. Min Act: -0.1700
Data Index: 4832478 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4812. Min Range: -6.4812
Max Act: 5.5437. Min Act: -0.1700
Data Index: 6865970 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4812. Min Range: -6.4812
Max Act: 5.4812. Min Act: -0.1700
Data Index: 1986413 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4812. Min Range: -6.4812
Max Act: 5.5125. Min Act: -0.1700
Data Index: 8682181 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4812. Min Range: -6.4812
Max Act: 5.4812. Min Act: -0.1700
Data Index: 1958287 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #19