Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6369 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6182. Min Range: -6.6182
Max Act: 6.6182. Min Act: -0.1700
Data Index: 5154356 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6182. Min Range: -6.6182
Max Act: 6.3995. Min Act: -0.1700
Data Index: 1239184 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6182. Min Range: -6.6182
Max Act: 6.3057. Min Act: -0.1700
Data Index: 581153 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6182. Min Range: -6.6182
Max Act: 6.2432. Min Act: -0.1700
Data Index: 4324781 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6182. Min Range: -6.6182
Max Act: 6.2432. Min Act: -0.1700
Data Index: 8546041 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6182. Min Range: -6.6182
Max Act: 6.2432. Min Act: -0.1700
Data Index: 1686891 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6182. Min Range: -6.6182
Max Act: 6.1807. Min Act: -0.1700
Data Index: 1557612 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6182. Min Range: -6.6182
Max Act: 6.1495. Min Act: -0.1700
Data Index: 4984860 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6182. Min Range: -6.6182
Max Act: 6.1495. Min Act: -0.1700
Data Index: 337329 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6182. Min Range: -6.6182
Max Act: 6.1495. Min Act: -0.1700
Data Index: 1217348 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6182. Min Range: -6.6182
Max Act: 6.1182. Min Act: -0.1700
Data Index: 8260689 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6182. Min Range: -6.6182
Max Act: 6.1182. Min Act: -0.1700
Data Index: 386715 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6182. Min Range: -6.6182
Max Act: 6.0557. Min Act: -0.1700
Data Index: 2208456 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6182. Min Range: -6.6182
Max Act: 6.0870. Min Act: -0.1700
Data Index: 5380389 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6182. Min Range: -6.6182
Max Act: 6.0557. Min Act: -0.1700
Data Index: 4364775 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6182. Min Range: -6.6182
Max Act: 6.0245. Min Act: -0.1700
Data Index: 7638341 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6182. Min Range: -6.6182
Max Act: 6.0245. Min Act: -0.1700
Data Index: 1113944 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6182. Min Range: -6.6182
Max Act: 5.9932. Min Act: -0.1700
Data Index: 2611802 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6182. Min Range: -6.6182
Max Act: 5.9620. Min Act: -0.1700
Data Index: 1196353 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6182. Min Range: -6.6182
Max Act: 5.9932. Min Act: -0.1700
Data Index: 5428305 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #19