Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5773 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3119. Min Range: -6.3119
Max Act: 6.3119. Min Act: -0.1700
Data Index: 6714770 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3119. Min Range: -6.3119
Max Act: 6.2807. Min Act: -0.1700
Data Index: 7792405 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3119. Min Range: -6.3119
Max Act: 6.2182. Min Act: -0.1700
Data Index: 3148579 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3119. Min Range: -6.3119
Max Act: 6.1869. Min Act: -0.1700
Data Index: 581741 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3119. Min Range: -6.3119
Max Act: 6.1869. Min Act: -0.1700
Data Index: 1538102 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3119. Min Range: -6.3119
Max Act: 6.1557. Min Act: -0.1700
Data Index: 1473590 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3119. Min Range: -6.3119
Max Act: 6.1557. Min Act: -0.1700
Data Index: 3881824 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3119. Min Range: -6.3119
Max Act: 6.1244. Min Act: -0.1700
Data Index: 4231898 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3119. Min Range: -6.3119
Max Act: 6.0932. Min Act: -0.1700
Data Index: 6991700 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3119. Min Range: -6.3119
Max Act: 6.0307. Min Act: -0.1700
Data Index: 6862510 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3119. Min Range: -6.3119
Max Act: 5.9994. Min Act: -0.1700
Data Index: 3173100 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3119. Min Range: -6.3119
Max Act: 5.9994. Min Act: -0.1700
Data Index: 660505 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3119. Min Range: -6.3119
Max Act: 5.9994. Min Act: -0.1700
Data Index: 7003050 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3119. Min Range: -6.3119
Max Act: 5.9994. Min Act: -0.1700
Data Index: 8192666 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3119. Min Range: -6.3119
Max Act: 6.0307. Min Act: -0.1700
Data Index: 2165775 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3119. Min Range: -6.3119
Max Act: 5.9682. Min Act: -0.1700
Data Index: 8708264 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3119. Min Range: -6.3119
Max Act: 5.9994. Min Act: -0.1700
Data Index: 8480812 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3119. Min Range: -6.3119
Max Act: 5.9682. Min Act: -0.1700
Data Index: 3230113 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3119. Min Range: -6.3119
Max Act: 5.9682. Min Act: -0.1700
Data Index: 3324945 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3119. Min Range: -6.3119
Max Act: 5.9682. Min Act: -0.1700
Data Index: 129776 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19