Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 843 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3405. Min Range: -8.3405
Max Act: 8.3405. Min Act: -0.1700
Data Index: 6703817 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3405. Min Range: -8.3405
Max Act: 8.1530. Min Act: -0.1700
Data Index: 2630511 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3405. Min Range: -8.3405
Max Act: 8.2780. Min Act: -0.1700
Data Index: 6567580 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3405. Min Range: -8.3405
Max Act: 8.1530. Min Act: -0.1700
Data Index: 2097940 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3405. Min Range: -8.3405
Max Act: 7.9655. Min Act: -0.1700
Data Index: 6777402 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3405. Min Range: -8.3405
Max Act: 7.9655. Min Act: -0.1700
Data Index: 8277679 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3405. Min Range: -8.3405
Max Act: 7.9030. Min Act: -0.1700
Data Index: 8019554 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3405. Min Range: -8.3405
Max Act: 7.9030. Min Act: -0.1700
Data Index: 8554600 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3405. Min Range: -8.3405
Max Act: 7.9030. Min Act: -0.1700
Data Index: 1902666 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3405. Min Range: -8.3405
Max Act: 7.8405. Min Act: -0.1700
Data Index: 2828996 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3405. Min Range: -8.3405
Max Act: 7.8405. Min Act: -0.1700
Data Index: 2059435 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3405. Min Range: -8.3405
Max Act: 7.8405. Min Act: -0.1700
Data Index: 6021781 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3405. Min Range: -8.3405
Max Act: 7.8405. Min Act: -0.1700
Data Index: 8635562 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3405. Min Range: -8.3405
Max Act: 7.8405. Min Act: -0.1700
Data Index: 127434 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3405. Min Range: -8.3405
Max Act: 7.8405. Min Act: -0.1700
Data Index: 6324479 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3405. Min Range: -8.3405
Max Act: 7.8405. Min Act: -0.1700
Data Index: 4332456 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3405. Min Range: -8.3405
Max Act: 7.7780. Min Act: -0.1700
Data Index: 1707070 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3405. Min Range: -8.3405
Max Act: 7.7780. Min Act: -0.1700
Data Index: 3898451 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3405. Min Range: -8.3405
Max Act: 7.7780. Min Act: -0.1700
Data Index: 3203774 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3405. Min Range: -8.3405
Max Act: 7.7780. Min Act: -0.1700
Data Index: 4061244 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #19