Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3878 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2870. Min Range: -6.2870
Max Act: 6.2870. Min Act: -0.1700
Data Index: 2962783 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2870. Min Range: -6.2870
Max Act: 6.1932. Min Act: -0.1700
Data Index: 1950782 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2870. Min Range: -6.2870
Max Act: 6.1307. Min Act: -0.1700
Data Index: 383816 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2870. Min Range: -6.2870
Max Act: 6.0682. Min Act: -0.1700
Data Index: 6252780 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2870. Min Range: -6.2870
Max Act: 6.0370. Min Act: -0.1700
Data Index: 1561314 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2870. Min Range: -6.2870
Max Act: 5.9745. Min Act: -0.1700
Data Index: 3102378 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2870. Min Range: -6.2870
Max Act: 5.9745. Min Act: -0.1700
Data Index: 3631971 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2870. Min Range: -6.2870
Max Act: 5.9432. Min Act: -0.1700
Data Index: 651010 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2870. Min Range: -6.2870
Max Act: 5.9432. Min Act: -0.1700
Data Index: 5401107 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2870. Min Range: -6.2870
Max Act: 5.9120. Min Act: -0.1700
Data Index: 4637163 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2870. Min Range: -6.2870
Max Act: 5.9120. Min Act: -0.1700
Data Index: 7686073 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2870. Min Range: -6.2870
Max Act: 5.9120. Min Act: -0.1700
Data Index: 76022 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2870. Min Range: -6.2870
Max Act: 5.9120. Min Act: -0.1700
Data Index: 3078014 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2870. Min Range: -6.2870
Max Act: 5.8807. Min Act: -0.1700
Data Index: 5089125 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2870. Min Range: -6.2870
Max Act: 5.9120. Min Act: -0.1700
Data Index: 3694454 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2870. Min Range: -6.2870
Max Act: 5.8807. Min Act: -0.1700
Data Index: 5551161 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2870. Min Range: -6.2870
Max Act: 5.8807. Min Act: -0.1700
Data Index: 6106933 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2870. Min Range: -6.2870
Max Act: 5.8807. Min Act: -0.1700
Data Index: 2706302 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2870. Min Range: -6.2870
Max Act: 5.8495. Min Act: -0.1700
Data Index: 1918855 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2870. Min Range: -6.2870
Max Act: 5.8495. Min Act: -0.1700
Data Index: 1392775 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19