Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3204 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0250. Min Range: -6.0250
Max Act: 6.0250. Min Act: -0.1700
Data Index: 8398994 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0250. Min Range: -6.0250
Max Act: 5.9000. Min Act: -0.1700
Data Index: 8051072 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0250. Min Range: -6.0250
Max Act: 5.8375. Min Act: -0.1700
Data Index: 6962528 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0250. Min Range: -6.0250
Max Act: 5.7750. Min Act: -0.1700
Data Index: 6769295 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0250. Min Range: -6.0250
Max Act: 5.8375. Min Act: -0.1700
Data Index: 2525052 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0250. Min Range: -6.0250
Max Act: 5.8063. Min Act: -0.1700
Data Index: 1712300 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0250. Min Range: -6.0250
Max Act: 5.7750. Min Act: -0.1700
Data Index: 1314484 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0250. Min Range: -6.0250
Max Act: 5.7438. Min Act: -0.1700
Data Index: 6270115 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0250. Min Range: -6.0250
Max Act: 5.7438. Min Act: -0.1700
Data Index: 6070847 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0250. Min Range: -6.0250
Max Act: 5.7125. Min Act: -0.1700
Data Index: 1279372 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0250. Min Range: -6.0250
Max Act: 5.6813. Min Act: -0.1700
Data Index: 2393814 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0250. Min Range: -6.0250
Max Act: 5.7125. Min Act: -0.1700
Data Index: 3573483 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0250. Min Range: -6.0250
Max Act: 5.7125. Min Act: -0.1700
Data Index: 1734052 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0250. Min Range: -6.0250
Max Act: 5.6500. Min Act: -0.1700
Data Index: 8158005 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0250. Min Range: -6.0250
Max Act: 5.6813. Min Act: -0.1700
Data Index: 6451573 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0250. Min Range: -6.0250
Max Act: 5.6500. Min Act: -0.1700
Data Index: 7148998 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0250. Min Range: -6.0250
Max Act: 5.6813. Min Act: -0.1700
Data Index: 5599342 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0250. Min Range: -6.0250
Max Act: 5.6813. Min Act: -0.1700
Data Index: 1712274 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0250. Min Range: -6.0250
Max Act: 5.6813. Min Act: -0.1700
Data Index: 2679129 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0250. Min Range: -6.0250
Max Act: 5.6500. Min Act: -0.1700
Data Index: 8339667 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #19