Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2791 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9030. Min Range: -5.9030
Max Act: 5.9030. Min Act: -0.1700
Data Index: 3950589 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9030. Min Range: -5.9030
Max Act: 5.5905. Min Act: -0.1700
Data Index: 6840885 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9030. Min Range: -5.9030
Max Act: 5.5593. Min Act: -0.1700
Data Index: 4088934 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9030. Min Range: -5.9030
Max Act: 5.4968. Min Act: -0.1700
Data Index: 8005522 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9030. Min Range: -5.9030
Max Act: 5.4968. Min Act: -0.1700
Data Index: 4981184 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9030. Min Range: -5.9030
Max Act: 5.4343. Min Act: -0.1700
Data Index: 6889242 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9030. Min Range: -5.9030
Max Act: 5.3718. Min Act: -0.1700
Data Index: 3345133 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9030. Min Range: -5.9030
Max Act: 5.3405. Min Act: -0.1700
Data Index: 5134768 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9030. Min Range: -5.9030
Max Act: 5.3718. Min Act: -0.1700
Data Index: 7876488 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9030. Min Range: -5.9030
Max Act: 5.3718. Min Act: -0.1700
Data Index: 6266897 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9030. Min Range: -5.9030
Max Act: 5.3718. Min Act: -0.1700
Data Index: 4077361 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9030. Min Range: -5.9030
Max Act: 5.3405. Min Act: -0.1700
Data Index: 3432156 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9030. Min Range: -5.9030
Max Act: 5.3405. Min Act: -0.1700
Data Index: 6870683 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9030. Min Range: -5.9030
Max Act: 5.3405. Min Act: -0.1700
Data Index: 1626434 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9030. Min Range: -5.9030
Max Act: 5.3093. Min Act: -0.1700
Data Index: 8361690 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9030. Min Range: -5.9030
Max Act: 5.2780. Min Act: -0.1700
Data Index: 491754 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9030. Min Range: -5.9030
Max Act: 5.2780. Min Act: -0.1700
Data Index: 7740862 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9030. Min Range: -5.9030
Max Act: 5.3093. Min Act: -0.1700
Data Index: 4594291 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9030. Min Range: -5.9030
Max Act: 5.2468. Min Act: -0.1700
Data Index: 7452876 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9030. Min Range: -5.9030
Max Act: 5.2468. Min Act: -0.1700
Data Index: 5580605 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #19