Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5233 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7762. Min Range: -6.7762
Max Act: 6.7762. Min Act: -0.1700
Data Index: 2696788 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7762. Min Range: -6.7762
Max Act: 6.6824. Min Act: -0.1700
Data Index: 1741822 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7762. Min Range: -6.7762
Max Act: 6.6824. Min Act: -0.1700
Data Index: 3874278 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7762. Min Range: -6.7762
Max Act: 6.6824. Min Act: -0.1700
Data Index: 2522888 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7762. Min Range: -6.7762
Max Act: 6.6824. Min Act: -0.1700
Data Index: 4230644 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7762. Min Range: -6.7762
Max Act: 6.6824. Min Act: -0.1700
Data Index: 4386025 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7762. Min Range: -6.7762
Max Act: 6.6824. Min Act: -0.1700
Data Index: 1090497 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7762. Min Range: -6.7762
Max Act: 6.6824. Min Act: -0.1700
Data Index: 1257297 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7762. Min Range: -6.7762
Max Act: 6.6512. Min Act: -0.1700
Data Index: 7558889 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7762. Min Range: -6.7762
Max Act: 6.6512. Min Act: -0.1700
Data Index: 1285042 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7762. Min Range: -6.7762
Max Act: 6.6512. Min Act: -0.1700
Data Index: 2327698 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7762. Min Range: -6.7762
Max Act: 6.6512. Min Act: -0.1700
Data Index: 2498 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7762. Min Range: -6.7762
Max Act: 6.6512. Min Act: -0.1700
Data Index: 7010339 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7762. Min Range: -6.7762
Max Act: 6.6512. Min Act: -0.1700
Data Index: 5136570 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7762. Min Range: -6.7762
Max Act: 6.6512. Min Act: -0.1700
Data Index: 4592331 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7762. Min Range: -6.7762
Max Act: 6.6512. Min Act: -0.1700
Data Index: 4451053 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7762. Min Range: -6.7762
Max Act: 6.6824. Min Act: -0.1700
Data Index: 1059114 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7762. Min Range: -6.7762
Max Act: 6.6512. Min Act: -0.1700
Data Index: 1967342 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7762. Min Range: -6.7762
Max Act: 6.6512. Min Act: -0.1700
Data Index: 3935972 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7762. Min Range: -6.7762
Max Act: 6.6512. Min Act: -0.1700
Data Index: 3630137 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #19