Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3495 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2061. Min Range: -6.2061
Max Act: 6.2061. Min Act: -0.1700
Data Index: 6159957 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2061. Min Range: -6.2061
Max Act: 6.1748. Min Act: -0.1700
Data Index: 2564643 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2061. Min Range: -6.2061
Max Act: 6.1748. Min Act: -0.1700
Data Index: 489804 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2061. Min Range: -6.2061
Max Act: 6.1436. Min Act: -0.1700
Data Index: 6586593 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2061. Min Range: -6.2061
Max Act: 6.0811. Min Act: -0.1700
Data Index: 4075124 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2061. Min Range: -6.2061
Max Act: 6.0811. Min Act: -0.1700
Data Index: 859672 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2061. Min Range: -6.2061
Max Act: 6.0498. Min Act: -0.1700
Data Index: 3102059 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2061. Min Range: -6.2061
Max Act: 5.9873. Min Act: -0.1700
Data Index: 6768797 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2061. Min Range: -6.2061
Max Act: 5.9873. Min Act: -0.1700
Data Index: 2609666 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2061. Min Range: -6.2061
Max Act: 5.9561. Min Act: -0.1700
Data Index: 4315424 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2061. Min Range: -6.2061
Max Act: 5.8936. Min Act: -0.1700
Data Index: 65798 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2061. Min Range: -6.2061
Max Act: 5.8936. Min Act: -0.1700
Data Index: 4065961 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2061. Min Range: -6.2061
Max Act: 5.8936. Min Act: -0.1700
Data Index: 18537 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2061. Min Range: -6.2061
Max Act: 5.8623. Min Act: -0.1700
Data Index: 2709140 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2061. Min Range: -6.2061
Max Act: 5.8936. Min Act: -0.1700
Data Index: 940786 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2061. Min Range: -6.2061
Max Act: 5.7998. Min Act: -0.1700
Data Index: 129227 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2061. Min Range: -6.2061
Max Act: 5.8311. Min Act: -0.1700
Data Index: 5264993 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2061. Min Range: -6.2061
Max Act: 5.8311. Min Act: -0.1700
Data Index: 7882143 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2061. Min Range: -6.2061
Max Act: 5.7998. Min Act: -0.1700
Data Index: 821120 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2061. Min Range: -6.2061
Max Act: 5.8311. Min Act: -0.1700
Data Index: 7357989 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #19