Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3527 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9028. Min Range: -4.9028
Max Act: 4.9028. Min Act: -0.1700
Data Index: 690115 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9028. Min Range: -4.9028
Max Act: 4.9028. Min Act: -0.1700
Data Index: 6300961 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9028. Min Range: -4.9028
Max Act: 4.9028. Min Act: -0.1700
Data Index: 4552252 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9028. Min Range: -4.9028
Max Act: 4.8715. Min Act: -0.1700
Data Index: 8709952 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9028. Min Range: -4.9028
Max Act: 4.8403. Min Act: -0.1700
Data Index: 7119929 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9028. Min Range: -4.9028
Max Act: 4.8715. Min Act: -0.1700
Data Index: 2147865 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9028. Min Range: -4.9028
Max Act: 4.8715. Min Act: -0.1700
Data Index: 2336147 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9028. Min Range: -4.9028
Max Act: 4.8403. Min Act: -0.1700
Data Index: 8325577 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9028. Min Range: -4.9028
Max Act: 4.8403. Min Act: -0.1700
Data Index: 8269630 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9028. Min Range: -4.9028
Max Act: 4.8090. Min Act: -0.1700
Data Index: 3309404 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9028. Min Range: -4.9028
Max Act: 4.8403. Min Act: -0.1699
Data Index: 7327150 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9028. Min Range: -4.9028
Max Act: 4.8090. Min Act: -0.1700
Data Index: 7702864 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9028. Min Range: -4.9028
Max Act: 4.8090. Min Act: -0.1700
Data Index: 7875029 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9028. Min Range: -4.9028
Max Act: 4.8090. Min Act: -0.1700
Data Index: 4321769 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9028. Min Range: -4.9028
Max Act: 4.8090. Min Act: -0.1700
Data Index: 2555727 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9028. Min Range: -4.9028
Max Act: 4.8403. Min Act: -0.1700
Data Index: 2589859 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9028. Min Range: -4.9028
Max Act: 4.8090. Min Act: -0.1700
Data Index: 1444695 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9028. Min Range: -4.9028
Max Act: 4.8090. Min Act: -0.1700
Data Index: 4555461 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9028. Min Range: -4.9028
Max Act: 4.8090. Min Act: -0.1700
Data Index: 5231547 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9028. Min Range: -4.9028
Max Act: 4.8090. Min Act: -0.1700
Data Index: 3098700 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19