Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3007 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5099. Min Range: -6.5099
Max Act: 6.5099. Min Act: -0.1700
Data Index: 1772442 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5099. Min Range: -6.5099
Max Act: 6.4474. Min Act: -0.1700
Data Index: 974378 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5099. Min Range: -6.5099
Max Act: 6.1974. Min Act: -0.1700
Data Index: 5911148 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5099. Min Range: -6.5099
Max Act: 6.1037. Min Act: -0.1700
Data Index: 8435147 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5099. Min Range: -6.5099
Max Act: 6.0724. Min Act: -0.1700
Data Index: 1824481 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5099. Min Range: -6.5099
Max Act: 6.0412. Min Act: -0.1700
Data Index: 570736 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5099. Min Range: -6.5099
Max Act: 6.0412. Min Act: -0.1700
Data Index: 8787867 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5099. Min Range: -6.5099
Max Act: 6.0412. Min Act: -0.1700
Data Index: 3505916 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5099. Min Range: -6.5099
Max Act: 5.9162. Min Act: -0.1700
Data Index: 7614203 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5099. Min Range: -6.5099
Max Act: 5.9162. Min Act: -0.1700
Data Index: 6944284 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5099. Min Range: -6.5099
Max Act: 5.9162. Min Act: -0.1700
Data Index: 7665077 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5099. Min Range: -6.5099
Max Act: 5.9474. Min Act: -0.1700
Data Index: 6196124 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5099. Min Range: -6.5099
Max Act: 5.8849. Min Act: -0.1700
Data Index: 6284810 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5099. Min Range: -6.5099
Max Act: 5.8849. Min Act: -0.1700
Data Index: 1106881 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5099. Min Range: -6.5099
Max Act: 5.8849. Min Act: -0.1700
Data Index: 4909491 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5099. Min Range: -6.5099
Max Act: 5.8849. Min Act: -0.1700
Data Index: 6816779 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5099. Min Range: -6.5099
Max Act: 5.8849. Min Act: -0.1700
Data Index: 8761303 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5099. Min Range: -6.5099
Max Act: 5.8537. Min Act: -0.1700
Data Index: 4369972 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5099. Min Range: -6.5099
Max Act: 5.8537. Min Act: -0.1700
Data Index: 2152177 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5099. Min Range: -6.5099
Max Act: 5.8849. Min Act: -0.1700
Data Index: 4738704 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19