Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3369 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4433. Min Range: -6.4433
Max Act: 6.4433. Min Act: -0.1700
Data Index: 5685478 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4433. Min Range: -6.4433
Max Act: 6.0995. Min Act: -0.1700
Data Index: 5148802 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4433. Min Range: -6.4433
Max Act: 6.0683. Min Act: -0.1700
Data Index: 1327821 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4433. Min Range: -6.4433
Max Act: 6.0683. Min Act: -0.1700
Data Index: 7796908 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4433. Min Range: -6.4433
Max Act: 6.0683. Min Act: -0.1700
Data Index: 678678 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4433. Min Range: -6.4433
Max Act: 6.0370. Min Act: -0.1700
Data Index: 8277541 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4433. Min Range: -6.4433
Max Act: 6.0058. Min Act: -0.1700
Data Index: 3070151 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4433. Min Range: -6.4433
Max Act: 5.9745. Min Act: -0.1700
Data Index: 7564637 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4433. Min Range: -6.4433
Max Act: 5.9433. Min Act: -0.1700
Data Index: 7862673 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4433. Min Range: -6.4433
Max Act: 5.9433. Min Act: -0.1700
Data Index: 2833363 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4433. Min Range: -6.4433
Max Act: 5.8808. Min Act: -0.1700
Data Index: 6897232 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4433. Min Range: -6.4433
Max Act: 5.8808. Min Act: -0.1700
Data Index: 6989984 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4433. Min Range: -6.4433
Max Act: 5.9120. Min Act: -0.1700
Data Index: 1331858 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4433. Min Range: -6.4433
Max Act: 5.8808. Min Act: -0.1700
Data Index: 5432111 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4433. Min Range: -6.4433
Max Act: 5.8808. Min Act: -0.1700
Data Index: 3491233 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4433. Min Range: -6.4433
Max Act: 5.8808. Min Act: -0.1700
Data Index: 1699060 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4433. Min Range: -6.4433
Max Act: 5.8495. Min Act: -0.1700
Data Index: 188847 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4433. Min Range: -6.4433
Max Act: 5.7558. Min Act: -0.1700
Data Index: 2171808 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4433. Min Range: -6.4433
Max Act: 5.7870. Min Act: -0.1700
Data Index: 3797642 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4433. Min Range: -6.4433
Max Act: 5.7558. Min Act: -0.1700
Data Index: 3780116 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19