Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3443 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2862. Min Range: -5.2862
Max Act: 5.2862. Min Act: -0.1700
Data Index: 4092260 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2862. Min Range: -5.2862
Max Act: 5.0050. Min Act: -0.1700
Data Index: 5507280 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2862. Min Range: -5.2862
Max Act: 5.0050. Min Act: -0.1700
Data Index: 1300617 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2862. Min Range: -5.2862
Max Act: 5.0050. Min Act: -0.1700
Data Index: 2600267 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2862. Min Range: -5.2862
Max Act: 4.9737. Min Act: -0.1700
Data Index: 6675887 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2862. Min Range: -5.2862
Max Act: 5.0050. Min Act: -0.1700
Data Index: 2369305 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2862. Min Range: -5.2862
Max Act: 4.9737. Min Act: -0.1700
Data Index: 6654102 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2862. Min Range: -5.2862
Max Act: 4.9425. Min Act: -0.1700
Data Index: 112670 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2862. Min Range: -5.2862
Max Act: 4.8800. Min Act: -0.1700
Data Index: 6578003 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2862. Min Range: -5.2862
Max Act: 4.8800. Min Act: -0.1700
Data Index: 7023473 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2862. Min Range: -5.2862
Max Act: 4.8800. Min Act: -0.1700
Data Index: 8553480 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2862. Min Range: -5.2862
Max Act: 4.7862. Min Act: -0.1700
Data Index: 2951617 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2862. Min Range: -5.2862
Max Act: 4.8175. Min Act: -0.1700
Data Index: 3003245 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2862. Min Range: -5.2862
Max Act: 4.7862. Min Act: -0.1700
Data Index: 7169846 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2862. Min Range: -5.2862
Max Act: 4.7862. Min Act: -0.1700
Data Index: 2785725 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2862. Min Range: -5.2862
Max Act: 4.7862. Min Act: -0.1700
Data Index: 37818 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2862. Min Range: -5.2862
Max Act: 4.7550. Min Act: -0.1700
Data Index: 7083696 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2862. Min Range: -5.2862
Max Act: 4.7550. Min Act: -0.1700
Data Index: 169159 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2862. Min Range: -5.2862
Max Act: 4.7237. Min Act: -0.1700
Data Index: 5731070 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2862. Min Range: -5.2862
Max Act: 4.7550. Min Act: -0.1700
Data Index: 2951631 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #19