Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3440 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8297. Min Range: -7.8297
Max Act: 7.8297. Min Act: -0.1700
Data Index: 8436254 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8297. Min Range: -7.8297
Max Act: 7.1734. Min Act: -0.1700
Data Index: 7501932 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8297. Min Range: -7.8297
Max Act: 7.0172. Min Act: -0.1700
Data Index: 6917488 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8297. Min Range: -7.8297
Max Act: 6.7984. Min Act: -0.1700
Data Index: 5030042 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8297. Min Range: -7.8297
Max Act: 6.8297. Min Act: -0.1700
Data Index: 838340 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8297. Min Range: -7.8297
Max Act: 6.7672. Min Act: -0.1700
Data Index: 6341656 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8297. Min Range: -7.8297
Max Act: 6.7984. Min Act: -0.1700
Data Index: 5760677 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8297. Min Range: -7.8297
Max Act: 6.7672. Min Act: -0.1700
Data Index: 3528132 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8297. Min Range: -7.8297
Max Act: 6.7672. Min Act: -0.1700
Data Index: 6887358 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8297. Min Range: -7.8297
Max Act: 6.7047. Min Act: -0.1700
Data Index: 890983 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8297. Min Range: -7.8297
Max Act: 6.7047. Min Act: -0.1700
Data Index: 5065799 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8297. Min Range: -7.8297
Max Act: 6.7047. Min Act: -0.1700
Data Index: 1735924 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8297. Min Range: -7.8297
Max Act: 6.6734. Min Act: -0.1700
Data Index: 3415920 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8297. Min Range: -7.8297
Max Act: 6.6734. Min Act: -0.1700
Data Index: 3720222 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8297. Min Range: -7.8297
Max Act: 6.7047. Min Act: -0.1700
Data Index: 7245592 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8297. Min Range: -7.8297
Max Act: 6.6734. Min Act: -0.1700
Data Index: 2529695 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8297. Min Range: -7.8297
Max Act: 6.6734. Min Act: -0.1700
Data Index: 8129919 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8297. Min Range: -7.8297
Max Act: 6.6422. Min Act: -0.1700
Data Index: 5236798 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8297. Min Range: -7.8297
Max Act: 6.6109. Min Act: -0.1700
Data Index: 1765781 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8297. Min Range: -7.8297
Max Act: 6.6734. Min Act: -0.1700
Data Index: 6873446 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19