Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2808 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4346. Min Range: -6.4346
Max Act: 6.4346. Min Act: -0.1700
Data Index: 1049930 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4346. Min Range: -6.4346
Max Act: 6.3721. Min Act: -0.1700
Data Index: 681785 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4346. Min Range: -6.4346
Max Act: 6.0908. Min Act: -0.1700
Data Index: 2298465 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4346. Min Range: -6.4346
Max Act: 5.9971. Min Act: -0.1700
Data Index: 6018033 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4346. Min Range: -6.4346
Max Act: 5.9346. Min Act: -0.1700
Data Index: 4357573 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4346. Min Range: -6.4346
Max Act: 5.9346. Min Act: -0.1700
Data Index: 6911850 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4346. Min Range: -6.4346
Max Act: 5.9346. Min Act: -0.1700
Data Index: 6089241 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4346. Min Range: -6.4346
Max Act: 5.8721. Min Act: -0.1700
Data Index: 927920 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4346. Min Range: -6.4346
Max Act: 5.8721. Min Act: -0.1700
Data Index: 7838415 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4346. Min Range: -6.4346
Max Act: 5.8408. Min Act: -0.1700
Data Index: 4887741 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4346. Min Range: -6.4346
Max Act: 5.8408. Min Act: -0.1700
Data Index: 2587698 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4346. Min Range: -6.4346
Max Act: 5.8096. Min Act: -0.1700
Data Index: 7289890 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4346. Min Range: -6.4346
Max Act: 5.8096. Min Act: -0.1700
Data Index: 8289105 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4346. Min Range: -6.4346
Max Act: 5.8096. Min Act: -0.1700
Data Index: 439120 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4346. Min Range: -6.4346
Max Act: 5.7471. Min Act: -0.1700
Data Index: 8163117 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4346. Min Range: -6.4346
Max Act: 5.8096. Min Act: -0.1700
Data Index: 1183894 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4346. Min Range: -6.4346
Max Act: 5.7158. Min Act: -0.1700
Data Index: 4570044 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4346. Min Range: -6.4346
Max Act: 5.7471. Min Act: -0.1700
Data Index: 4460647 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4346. Min Range: -6.4346
Max Act: 5.7783. Min Act: -0.1700
Data Index: 529653 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4346. Min Range: -6.4346
Max Act: 5.7158. Min Act: -0.1700
Data Index: 4652039 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #19