Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3578 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0675. Min Range: -10.0675
Max Act: 10.0675. Min Act: -0.1700
Data Index: 4194028 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0675. Min Range: -10.0675
Max Act: 10.0050. Min Act: -0.1700
Data Index: 8094082 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0675. Min Range: -10.0675
Max Act: 10.0050. Min Act: -0.1700
Data Index: 8106787 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0675. Min Range: -10.0675
Max Act: 10.0050. Min Act: -0.1700
Data Index: 1357609 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0675. Min Range: -10.0675
Max Act: 10.0050. Min Act: -0.1700
Data Index: 8445195 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0675. Min Range: -10.0675
Max Act: 9.9425. Min Act: -0.1700
Data Index: 2945940 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0675. Min Range: -10.0675
Max Act: 9.8800. Min Act: -0.1700
Data Index: 5554133 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0675. Min Range: -10.0675
Max Act: 9.8800. Min Act: -0.1700
Data Index: 3119267 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0675. Min Range: -10.0675
Max Act: 9.8800. Min Act: -0.1700
Data Index: 4808851 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0675. Min Range: -10.0675
Max Act: 9.8800. Min Act: -0.1700
Data Index: 673834 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0675. Min Range: -10.0675
Max Act: 9.8800. Min Act: -0.1700
Data Index: 2343094 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0675. Min Range: -10.0675
Max Act: 9.8175. Min Act: -0.1700
Data Index: 7376395 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0675. Min Range: -10.0675
Max Act: 9.8175. Min Act: -0.1700
Data Index: 1777208 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0675. Min Range: -10.0675
Max Act: 9.7550. Min Act: -0.1700
Data Index: 7471625 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0675. Min Range: -10.0675
Max Act: 9.8800. Min Act: -0.1700
Data Index: 4424964 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0675. Min Range: -10.0675
Max Act: 9.8175. Min Act: -0.1700
Data Index: 2036403 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0675. Min Range: -10.0675
Max Act: 9.7550. Min Act: -0.1700
Data Index: 870432 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0675. Min Range: -10.0675
Max Act: 9.7550. Min Act: -0.1700
Data Index: 6281802 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0675. Min Range: -10.0675
Max Act: 9.7550. Min Act: -0.1700
Data Index: 593377 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0675. Min Range: -10.0675
Max Act: 9.6925. Min Act: -0.1700
Data Index: 4382585 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #19