Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4682 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1789. Min Range: -5.1789
Max Act: 5.1789. Min Act: -0.1700
Data Index: 6494483 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1789. Min Range: -5.1789
Max Act: 5.1789. Min Act: -0.1700
Data Index: 2602776 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1789. Min Range: -5.1789
Max Act: 5.1789. Min Act: -0.1700
Data Index: 6008837 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1789. Min Range: -5.1789
Max Act: 5.1164. Min Act: -0.1700
Data Index: 5093664 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1789. Min Range: -5.1789
Max Act: 5.0851. Min Act: -0.1700
Data Index: 7379634 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1789. Min Range: -5.1789
Max Act: 5.0539. Min Act: -0.1700
Data Index: 3376781 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1789. Min Range: -5.1789
Max Act: 5.0851. Min Act: -0.1700
Data Index: 8505853 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1789. Min Range: -5.1789
Max Act: 5.0539. Min Act: -0.1700
Data Index: 774379 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1789. Min Range: -5.1789
Max Act: 5.0539. Min Act: -0.1700
Data Index: 4882123 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1789. Min Range: -5.1789
Max Act: 4.9914. Min Act: -0.1700
Data Index: 1043863 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1789. Min Range: -5.1789
Max Act: 5.0226. Min Act: -0.1700
Data Index: 4167771 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1789. Min Range: -5.1789
Max Act: 4.9914. Min Act: -0.1700
Data Index: 2592884 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1789. Min Range: -5.1789
Max Act: 4.9914. Min Act: -0.1700
Data Index: 4464375 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1789. Min Range: -5.1789
Max Act: 4.9914. Min Act: -0.1700
Data Index: 6666182 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1789. Min Range: -5.1789
Max Act: 4.9914. Min Act: -0.1700
Data Index: 4456249 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1789. Min Range: -5.1789
Max Act: 4.9914. Min Act: -0.1700
Data Index: 7038351 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1789. Min Range: -5.1789
Max Act: 4.9914. Min Act: -0.1700
Data Index: 4375049 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1789. Min Range: -5.1789
Max Act: 4.9601. Min Act: -0.1700
Data Index: 1357856 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1789. Min Range: -5.1789
Max Act: 4.9601. Min Act: -0.1700
Data Index: 1546449 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1789. Min Range: -5.1789
Max Act: 4.9289. Min Act: -0.1700
Data Index: 1137740 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19