Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2975 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.1433. Min Range: -2.1433
Max Act: 2.1433. Min Act: -0.1700
Data Index: 4700073 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1433. Min Range: -2.1433
Max Act: 2.1433. Min Act: -0.1700
Data Index: 2940582 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1433. Min Range: -2.1433
Max Act: 2.1099. Min Act: -0.1700
Data Index: 1509995 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1433. Min Range: -2.1433
Max Act: 2.0595. Min Act: -0.1700
Data Index: 5004823 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1433. Min Range: -2.1433
Max Act: 2.0763. Min Act: -0.1700
Data Index: 2788728 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1433. Min Range: -2.1433
Max Act: 2.0427. Min Act: -0.1700
Data Index: 5266220 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1433. Min Range: -2.1433
Max Act: 2.0427. Min Act: -0.1700
Data Index: 6846409 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1433. Min Range: -2.1433
Max Act: 2.0259. Min Act: -0.1700
Data Index: 2131365 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1433. Min Range: -2.1433
Max Act: 2.0090. Min Act: -0.1700
Data Index: 8357437 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1433. Min Range: -2.1433
Max Act: 2.0090. Min Act: -0.1700
Data Index: 512458 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1433. Min Range: -2.1433
Max Act: 1.9921. Min Act: -0.1700
Data Index: 410203 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1433. Min Range: -2.1433
Max Act: 1.9921. Min Act: -0.1700
Data Index: 7668751 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1433. Min Range: -2.1433
Max Act: 1.9752. Min Act: -0.1700
Data Index: 3318920 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1433. Min Range: -2.1433
Max Act: 2.0090. Min Act: -0.1700
Data Index: 7849700 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1433. Min Range: -2.1433
Max Act: 1.9921. Min Act: -0.1700
Data Index: 4285757 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1433. Min Range: -2.1433
Max Act: 1.9752. Min Act: -0.1700
Data Index: 1321109 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1433. Min Range: -2.1433
Max Act: 1.9582. Min Act: -0.1700
Data Index: 6824149 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1433. Min Range: -2.1433
Max Act: 1.9752. Min Act: -0.1700
Data Index: 4039356 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1433. Min Range: -2.1433
Max Act: 1.9921. Min Act: -0.1700
Data Index: 7895787 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1433. Min Range: -2.1433
Max Act: 1.9752. Min Act: -0.1700
Data Index: 6824150 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19