Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1551 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1870. Min Range: -6.1870
Max Act: 6.1870. Min Act: -0.1700
Data Index: 1334727 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1870. Min Range: -6.1870
Max Act: 6.1870. Min Act: -0.1700
Data Index: 1296831 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1870. Min Range: -6.1870
Max Act: 6.0308. Min Act: -0.1700
Data Index: 8579066 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1870. Min Range: -6.1870
Max Act: 5.9995. Min Act: -0.1700
Data Index: 6041785 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1870. Min Range: -6.1870
Max Act: 5.9370. Min Act: -0.1700
Data Index: 3558952 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1870. Min Range: -6.1870
Max Act: 5.9058. Min Act: -0.1700
Data Index: 742842 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1870. Min Range: -6.1870
Max Act: 5.8745. Min Act: -0.1700
Data Index: 3536447 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1870. Min Range: -6.1870
Max Act: 5.8745. Min Act: -0.1700
Data Index: 3402615 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1870. Min Range: -6.1870
Max Act: 5.8745. Min Act: -0.1700
Data Index: 7916901 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1870. Min Range: -6.1870
Max Act: 5.8433. Min Act: -0.1700
Data Index: 2776676 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1870. Min Range: -6.1870
Max Act: 5.8745. Min Act: -0.1700
Data Index: 3836758 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1870. Min Range: -6.1870
Max Act: 5.8745. Min Act: -0.1700
Data Index: 1524971 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1870. Min Range: -6.1870
Max Act: 5.8433. Min Act: -0.1700
Data Index: 6163561 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1870. Min Range: -6.1870
Max Act: 5.8433. Min Act: -0.1700
Data Index: 2982266 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1870. Min Range: -6.1870
Max Act: 5.8433. Min Act: -0.1700
Data Index: 7623663 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1870. Min Range: -6.1870
Max Act: 5.8433. Min Act: -0.1700
Data Index: 227291 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1870. Min Range: -6.1870
Max Act: 5.8433. Min Act: -0.1700
Data Index: 7952591 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1870. Min Range: -6.1870
Max Act: 5.8433. Min Act: -0.1700
Data Index: 2525740 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1870. Min Range: -6.1870
Max Act: 5.8433. Min Act: -0.1700
Data Index: 1017205 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1870. Min Range: -6.1870
Max Act: 5.8120. Min Act: -0.1700
Data Index: 1766256 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19