Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3475 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4870. Min Range: -7.4870
Max Act: 7.4870. Min Act: -0.1700
Data Index: 1706758 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4870. Min Range: -7.4870
Max Act: 7.4245. Min Act: -0.1700
Data Index: 5643677 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4870. Min Range: -7.4870
Max Act: 7.2057. Min Act: -0.1700
Data Index: 5261482 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4870. Min Range: -7.4870
Max Act: 7.1745. Min Act: -0.1700
Data Index: 6384078 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4870. Min Range: -7.4870
Max Act: 7.1745. Min Act: -0.1700
Data Index: 2114311 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4870. Min Range: -7.4870
Max Act: 7.1120. Min Act: -0.1700
Data Index: 6062713 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4870. Min Range: -7.4870
Max Act: 6.9557. Min Act: -0.1700
Data Index: 5469148 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4870. Min Range: -7.4870
Max Act: 6.9245. Min Act: -0.1700
Data Index: 1802441 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4870. Min Range: -7.4870
Max Act: 6.9245. Min Act: -0.1700
Data Index: 6562935 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4870. Min Range: -7.4870
Max Act: 6.8620. Min Act: -0.1700
Data Index: 7273192 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4870. Min Range: -7.4870
Max Act: 6.8932. Min Act: -0.1700
Data Index: 1125287 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4870. Min Range: -7.4870
Max Act: 6.8932. Min Act: -0.1700
Data Index: 5073436 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4870. Min Range: -7.4870
Max Act: 6.8307. Min Act: -0.1700
Data Index: 6783 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4870. Min Range: -7.4870
Max Act: 6.8307. Min Act: -0.1700
Data Index: 6981970 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4870. Min Range: -7.4870
Max Act: 6.7995. Min Act: -0.1700
Data Index: 4143594 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4870. Min Range: -7.4870
Max Act: 6.7995. Min Act: -0.1700
Data Index: 2346908 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4870. Min Range: -7.4870
Max Act: 6.7995. Min Act: -0.1700
Data Index: 3203611 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4870. Min Range: -7.4870
Max Act: 6.7995. Min Act: -0.1700
Data Index: 6006875 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4870. Min Range: -7.4870
Max Act: 6.7995. Min Act: -0.1700
Data Index: 14526 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4870. Min Range: -7.4870
Max Act: 6.7682. Min Act: -0.1700
Data Index: 173998 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19