Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5076 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0185. Min Range: -5.0185
Max Act: 5.0185. Min Act: -0.1700
Data Index: 8783770 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0185. Min Range: -5.0185
Max Act: 4.9560. Min Act: -0.1700
Data Index: 6674137 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0185. Min Range: -5.0185
Max Act: 4.9560. Min Act: -0.1700
Data Index: 702698 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0185. Min Range: -5.0185
Max Act: 4.9247. Min Act: -0.1700
Data Index: 249033 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0185. Min Range: -5.0185
Max Act: 4.9247. Min Act: -0.1700
Data Index: 261723 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0185. Min Range: -5.0185
Max Act: 4.9247. Min Act: -0.1700
Data Index: 2912713 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0185. Min Range: -5.0185
Max Act: 4.8935. Min Act: -0.1700
Data Index: 7854356 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0185. Min Range: -5.0185
Max Act: 4.8622. Min Act: -0.1700
Data Index: 1374014 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0185. Min Range: -5.0185
Max Act: 4.8935. Min Act: -0.1700
Data Index: 8620760 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0185. Min Range: -5.0185
Max Act: 4.8622. Min Act: -0.1700
Data Index: 8100107 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0185. Min Range: -5.0185
Max Act: 4.8622. Min Act: -0.1700
Data Index: 8620761 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0185. Min Range: -5.0185
Max Act: 4.8622. Min Act: -0.1700
Data Index: 2697966 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0185. Min Range: -5.0185
Max Act: 4.7997. Min Act: -0.1700
Data Index: 2887323 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0185. Min Range: -5.0185
Max Act: 4.7997. Min Act: -0.1700
Data Index: 121474 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0185. Min Range: -5.0185
Max Act: 4.7997. Min Act: -0.1700
Data Index: 6983688 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0185. Min Range: -5.0185
Max Act: 4.7997. Min Act: -0.1700
Data Index: 5157495 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0185. Min Range: -5.0185
Max Act: 4.7997. Min Act: -0.1700
Data Index: 1929423 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0185. Min Range: -5.0185
Max Act: 4.7997. Min Act: -0.1700
Data Index: 5078067 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0185. Min Range: -5.0185
Max Act: 4.7997. Min Act: -0.1700
Data Index: 5861696 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0185. Min Range: -5.0185
Max Act: 4.7685. Min Act: -0.1700
Data Index: 5380480 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19