Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5836 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9884. Min Range: -5.9884
Max Act: 5.9884. Min Act: -0.1700
Data Index: 6014118 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9884. Min Range: -5.9884
Max Act: 5.9884. Min Act: -0.1700
Data Index: 5110159 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9884. Min Range: -5.9884
Max Act: 5.8634. Min Act: -0.1700
Data Index: 1836785 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9884. Min Range: -5.9884
Max Act: 5.8634. Min Act: -0.1700
Data Index: 3536296 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9884. Min Range: -5.9884
Max Act: 5.7697. Min Act: -0.1700
Data Index: 3536297 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9884. Min Range: -5.9884
Max Act: 5.7697. Min Act: -0.1700
Data Index: 2977663 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9884. Min Range: -5.9884
Max Act: 5.7384. Min Act: -0.1700
Data Index: 3031682 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9884. Min Range: -5.9884
Max Act: 5.7072. Min Act: -0.1700
Data Index: 4331567 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9884. Min Range: -5.9884
Max Act: 5.7072. Min Act: -0.1700
Data Index: 2002952 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9884. Min Range: -5.9884
Max Act: 5.6759. Min Act: -0.1700
Data Index: 4213811 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9884. Min Range: -5.9884
Max Act: 5.6759. Min Act: -0.1700
Data Index: 892931 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9884. Min Range: -5.9884
Max Act: 5.6447. Min Act: -0.1700
Data Index: 28460 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9884. Min Range: -5.9884
Max Act: 5.6447. Min Act: -0.1700
Data Index: 2222757 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9884. Min Range: -5.9884
Max Act: 5.6134. Min Act: -0.1700
Data Index: 6917638 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9884. Min Range: -5.9884
Max Act: 5.6134. Min Act: -0.1700
Data Index: 5759914 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9884. Min Range: -5.9884
Max Act: 5.6134. Min Act: -0.1700
Data Index: 2808085 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9884. Min Range: -5.9884
Max Act: 5.6134. Min Act: -0.1700
Data Index: 668697 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9884. Min Range: -5.9884
Max Act: 5.5822. Min Act: -0.1700
Data Index: 6076968 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9884. Min Range: -5.9884
Max Act: 5.5822. Min Act: -0.1700
Data Index: 3730775 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9884. Min Range: -5.9884
Max Act: 5.5822. Min Act: -0.1700
Data Index: 414909 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #19