Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2785 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1759. Min Range: -8.1759
Max Act: 8.1759. Min Act: -0.1700
Data Index: 1835071 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1759. Min Range: -8.1759
Max Act: 8.1134. Min Act: -0.1700
Data Index: 4983148 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1759. Min Range: -8.1759
Max Act: 8.1134. Min Act: -0.1700
Data Index: 4255953 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1759. Min Range: -8.1759
Max Act: 8.0509. Min Act: -0.1700
Data Index: 4247587 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1759. Min Range: -8.1759
Max Act: 7.9884. Min Act: -0.1700
Data Index: 1847114 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1759. Min Range: -8.1759
Max Act: 7.9884. Min Act: -0.1700
Data Index: 4056873 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1759. Min Range: -8.1759
Max Act: 7.8634. Min Act: -0.1700
Data Index: 1595792 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1759. Min Range: -8.1759
Max Act: 7.8634. Min Act: -0.1700
Data Index: 3906486 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1759. Min Range: -8.1759
Max Act: 7.8634. Min Act: -0.1700
Data Index: 1352928 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1759. Min Range: -8.1759
Max Act: 7.8009. Min Act: -0.1700
Data Index: 4577342 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1759. Min Range: -8.1759
Max Act: 7.7384. Min Act: -0.1700
Data Index: 2949126 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1759. Min Range: -8.1759
Max Act: 7.7384. Min Act: -0.1700
Data Index: 6168180 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1759. Min Range: -8.1759
Max Act: 7.7384. Min Act: -0.1700
Data Index: 4416218 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1759. Min Range: -8.1759
Max Act: 7.8009. Min Act: -0.1700
Data Index: 7872554 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1759. Min Range: -8.1759
Max Act: 7.6759. Min Act: -0.1700
Data Index: 1244032 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1759. Min Range: -8.1759
Max Act: 7.7384. Min Act: -0.1700
Data Index: 3835834 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1759. Min Range: -8.1759
Max Act: 7.7384. Min Act: -0.1700
Data Index: 3282982 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1759. Min Range: -8.1759
Max Act: 7.7384. Min Act: -0.1700
Data Index: 888836 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1759. Min Range: -8.1759
Max Act: 7.7384. Min Act: -0.1700
Data Index: 80129 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1759. Min Range: -8.1759
Max Act: 7.7384. Min Act: -0.1700
Data Index: 1777081 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #19