Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 732 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4180. Min Range: -6.4180
Max Act: 6.4180. Min Act: -0.1700
Data Index: 1450023 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4180. Min Range: -6.4180
Max Act: 6.3555. Min Act: -0.1700
Data Index: 8698425 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4180. Min Range: -6.4180
Max Act: 6.2617. Min Act: -0.1700
Data Index: 277118 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4180. Min Range: -6.4180
Max Act: 6.2617. Min Act: -0.1700
Data Index: 4441476 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4180. Min Range: -6.4180
Max Act: 5.9805. Min Act: -0.1700
Data Index: 6187942 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4180. Min Range: -6.4180
Max Act: 5.9492. Min Act: -0.1700
Data Index: 3012799 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4180. Min Range: -6.4180
Max Act: 5.9492. Min Act: -0.1700
Data Index: 6530525 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4180. Min Range: -6.4180
Max Act: 5.8867. Min Act: -0.1700
Data Index: 1582013 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4180. Min Range: -6.4180
Max Act: 5.8867. Min Act: -0.1700
Data Index: 5163723 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4180. Min Range: -6.4180
Max Act: 5.8555. Min Act: -0.1700
Data Index: 2507707 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4180. Min Range: -6.4180
Max Act: 5.8242. Min Act: -0.1700
Data Index: 6742808 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4180. Min Range: -6.4180
Max Act: 5.7617. Min Act: -0.1700
Data Index: 6946327 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4180. Min Range: -6.4180
Max Act: 5.7617. Min Act: -0.1700
Data Index: 6809630 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4180. Min Range: -6.4180
Max Act: 5.6680. Min Act: -0.1700
Data Index: 2384405 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4180. Min Range: -6.4180
Max Act: 5.6367. Min Act: -0.1700
Data Index: 534800 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4180. Min Range: -6.4180
Max Act: 5.6367. Min Act: -0.1700
Data Index: 5654256 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4180. Min Range: -6.4180
Max Act: 5.6367. Min Act: -0.1700
Data Index: 5271875 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4180. Min Range: -6.4180
Max Act: 5.6367. Min Act: -0.1700
Data Index: 4013804 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4180. Min Range: -6.4180
Max Act: 5.6055. Min Act: -0.1700
Data Index: 6337265 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4180. Min Range: -6.4180
Max Act: 5.6055. Min Act: -0.1700
Data Index: 5861363 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19