Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3637 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0936. Min Range: -10.0936
Max Act: 10.0936. Min Act: -0.1700
Data Index: 61188 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0936. Min Range: -10.0936
Max Act: 9.9686. Min Act: -0.1700
Data Index: 2582540 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0936. Min Range: -10.0936
Max Act: 9.9061. Min Act: -0.1700
Data Index: 2808548 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0936. Min Range: -10.0936
Max Act: 9.9061. Min Act: -0.1700
Data Index: 3344556 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0936. Min Range: -10.0936
Max Act: 9.8436. Min Act: -0.1700
Data Index: 3993795 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0936. Min Range: -10.0936
Max Act: 9.7811. Min Act: -0.1700
Data Index: 2300459 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0936. Min Range: -10.0936
Max Act: 9.8436. Min Act: -0.1700
Data Index: 1834886 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0936. Min Range: -10.0936
Max Act: 9.7186. Min Act: -0.1700
Data Index: 4379109 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0936. Min Range: -10.0936
Max Act: 9.7186. Min Act: -0.1700
Data Index: 6614745 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0936. Min Range: -10.0936
Max Act: 9.6561. Min Act: -0.1700
Data Index: 8110637 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0936. Min Range: -10.0936
Max Act: 9.6561. Min Act: -0.1700
Data Index: 1584769 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0936. Min Range: -10.0936
Max Act: 9.5936. Min Act: -0.1700
Data Index: 3318445 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0936. Min Range: -10.0936
Max Act: 9.6561. Min Act: -0.1700
Data Index: 2903535 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0936. Min Range: -10.0936
Max Act: 9.6561. Min Act: -0.1700
Data Index: 5329764 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0936. Min Range: -10.0936
Max Act: 9.5936. Min Act: -0.1700
Data Index: 1181033 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0936. Min Range: -10.0936
Max Act: 9.5936. Min Act: -0.1700
Data Index: 5429161 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0936. Min Range: -10.0936
Max Act: 9.5936. Min Act: -0.1700
Data Index: 5312944 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0936. Min Range: -10.0936
Max Act: 9.5936. Min Act: -0.1700
Data Index: 3357159 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0936. Min Range: -10.0936
Max Act: 9.5936. Min Act: -0.1700
Data Index: 4981299 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0936. Min Range: -10.0936
Max Act: 9.5936. Min Act: -0.1700
Data Index: 280473 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19