Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3597 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4867. Min Range: -7.4867
Max Act: 7.4867. Min Act: -0.1700
Data Index: 3206394 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4867. Min Range: -7.4867
Max Act: 7.3930. Min Act: -0.1700
Data Index: 2602696 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4867. Min Range: -7.4867
Max Act: 7.2992. Min Act: -0.1700
Data Index: 6877959 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4867. Min Range: -7.4867
Max Act: 7.2992. Min Act: -0.1700
Data Index: 1665465 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4867. Min Range: -7.4867
Max Act: 7.1742. Min Act: -0.1700
Data Index: 4140292 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4867. Min Range: -7.4867
Max Act: 7.1430. Min Act: -0.1700
Data Index: 2946774 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4867. Min Range: -7.4867
Max Act: 7.0805. Min Act: -0.1700
Data Index: 2381848 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4867. Min Range: -7.4867
Max Act: 7.0805. Min Act: -0.1700
Data Index: 7164720 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4867. Min Range: -7.4867
Max Act: 7.0180. Min Act: -0.1700
Data Index: 3801419 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4867. Min Range: -7.4867
Max Act: 6.9867. Min Act: -0.1700
Data Index: 2507455 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4867. Min Range: -7.4867
Max Act: 7.0180. Min Act: -0.1700
Data Index: 3392801 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4867. Min Range: -7.4867
Max Act: 7.0180. Min Act: -0.1700
Data Index: 8200037 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4867. Min Range: -7.4867
Max Act: 6.9867. Min Act: -0.1700
Data Index: 2926277 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4867. Min Range: -7.4867
Max Act: 6.9555. Min Act: -0.1700
Data Index: 1401058 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4867. Min Range: -7.4867
Max Act: 6.9242. Min Act: -0.1700
Data Index: 1936520 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4867. Min Range: -7.4867
Max Act: 6.8617. Min Act: -0.1700
Data Index: 1333684 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4867. Min Range: -7.4867
Max Act: 6.8617. Min Act: -0.1700
Data Index: 7508943 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4867. Min Range: -7.4867
Max Act: 6.8930. Min Act: -0.1700
Data Index: 3907089 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4867. Min Range: -7.4867
Max Act: 6.8617. Min Act: -0.1700
Data Index: 6396908 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4867. Min Range: -7.4867
Max Act: 6.8305. Min Act: -0.1700
Data Index: 302297 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #19