Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4604 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.7668. Min Act: -0.1700
Data Index: 4162475 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.7043. Min Act: -0.1700
Data Index: 1738754 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.6730. Min Act: -0.1700
Data Index: 2459055 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.6730. Min Act: -0.1700
Data Index: 2780599 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.7043. Min Act: -0.1700
Data Index: 2459056 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.6418. Min Act: -0.1700
Data Index: 4426066 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.6418. Min Act: -0.1700
Data Index: 3712033 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.6105. Min Act: -0.1700
Data Index: 2870784 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.6105. Min Act: -0.1700
Data Index: 8257307 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.6105. Min Act: -0.1700
Data Index: 5771598 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.6105. Min Act: -0.1700
Data Index: 2388194 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.5793. Min Act: -0.1700
Data Index: 6616889 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.5793. Min Act: -0.1700
Data Index: 854190 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.5793. Min Act: -0.1700
Data Index: 4574850 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.5793. Min Act: -0.1700
Data Index: 2873434 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.5480. Min Act: -0.1700
Data Index: 2459054 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.5480. Min Act: -0.1700
Data Index: 876966 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.5480. Min Act: -0.1700
Data Index: 5475422 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.5480. Min Act: -0.1700
Data Index: 3695487 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.5793. Min Act: -0.1700
Data Index: 4247208 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19