Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4577 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3718. Min Range: -8.3718
Max Act: 8.3718. Min Act: -0.1700
Data Index: 2284316 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3718. Min Range: -8.3718
Max Act: 8.1843. Min Act: -0.1700
Data Index: 1228013 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3718. Min Range: -8.3718
Max Act: 8.1218. Min Act: -0.1700
Data Index: 1228019 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3718. Min Range: -8.3718
Max Act: 8.1218. Min Act: -0.1700
Data Index: 7687460 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3718. Min Range: -8.3718
Max Act: 8.0593. Min Act: -0.1700
Data Index: 1228018 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3718. Min Range: -8.3718
Max Act: 8.0593. Min Act: -0.1700
Data Index: 543993 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3718. Min Range: -8.3718
Max Act: 8.0593. Min Act: -0.1700
Data Index: 1228012 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3718. Min Range: -8.3718
Max Act: 7.9968. Min Act: -0.1700
Data Index: 7687461 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3718. Min Range: -8.3718
Max Act: 7.9343. Min Act: -0.1700
Data Index: 6961332 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3718. Min Range: -8.3718
Max Act: 7.9343. Min Act: -0.1700
Data Index: 6018110 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3718. Min Range: -8.3718
Max Act: 7.9968. Min Act: -0.1700
Data Index: 4639755 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3718. Min Range: -8.3718
Max Act: 7.9343. Min Act: -0.1700
Data Index: 7986263 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3718. Min Range: -8.3718
Max Act: 7.9343. Min Act: -0.1700
Data Index: 1228016 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3718. Min Range: -8.3718
Max Act: 7.8718. Min Act: -0.1700
Data Index: 1228020 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3718. Min Range: -8.3718
Max Act: 7.9343. Min Act: -0.1700
Data Index: 2213662 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3718. Min Range: -8.3718
Max Act: 7.8718. Min Act: -0.1700
Data Index: 798494 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3718. Min Range: -8.3718
Max Act: 7.8093. Min Act: -0.1700
Data Index: 2706877 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3718. Min Range: -8.3718
Max Act: 7.8718. Min Act: -0.1700
Data Index: 3745552 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3718. Min Range: -8.3718
Max Act: 7.8093. Min Act: -0.1700
Data Index: 3079309 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3718. Min Range: -8.3718
Max Act: 7.8093. Min Act: -0.1700
Data Index: 1228014 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19