Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5749 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3259. Min Range: -9.3259
Max Act: 9.3259. Min Act: -0.1700
Data Index: 2901696 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3259. Min Range: -9.3259
Max Act: 9.2634. Min Act: -0.1700
Data Index: 162896 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3259. Min Range: -9.3259
Max Act: 9.0759. Min Act: -0.1700
Data Index: 7515250 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3259. Min Range: -9.3259
Max Act: 9.0759. Min Act: -0.1700
Data Index: 7788521 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3259. Min Range: -9.3259
Max Act: 9.0759. Min Act: -0.1700
Data Index: 837350 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3259. Min Range: -9.3259
Max Act: 9.0134. Min Act: -0.1700
Data Index: 3558341 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3259. Min Range: -9.3259
Max Act: 9.0134. Min Act: -0.1700
Data Index: 6885233 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3259. Min Range: -9.3259
Max Act: 9.0134. Min Act: -0.1700
Data Index: 5927695 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3259. Min Range: -9.3259
Max Act: 9.0134. Min Act: -0.1700
Data Index: 5688177 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3259. Min Range: -9.3259
Max Act: 9.0134. Min Act: -0.1700
Data Index: 3967593 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3259. Min Range: -9.3259
Max Act: 8.9509. Min Act: -0.1700
Data Index: 17575 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3259. Min Range: -9.3259
Max Act: 8.9509. Min Act: -0.1700
Data Index: 6100624 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3259. Min Range: -9.3259
Max Act: 8.8884. Min Act: -0.1700
Data Index: 5342819 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3259. Min Range: -9.3259
Max Act: 8.8884. Min Act: -0.1700
Data Index: 6538334 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3259. Min Range: -9.3259
Max Act: 8.8884. Min Act: -0.1700
Data Index: 4003515 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3259. Min Range: -9.3259
Max Act: 8.8884. Min Act: -0.1700
Data Index: 6998249 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3259. Min Range: -9.3259
Max Act: 8.8884. Min Act: -0.1700
Data Index: 2958884 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3259. Min Range: -9.3259
Max Act: 8.8259. Min Act: -0.1700
Data Index: 8096630 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3259. Min Range: -9.3259
Max Act: 8.8884. Min Act: -0.1700
Data Index: 7329606 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3259. Min Range: -9.3259
Max Act: 8.8259. Min Act: -0.1700
Data Index: 6321400 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #19