Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4508 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0722. Min Range: -6.0722
Max Act: 6.0722. Min Act: -0.1700
Data Index: 4277784 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0722. Min Range: -6.0722
Max Act: 6.0722. Min Act: -0.1700
Data Index: 5541799 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0722. Min Range: -6.0722
Max Act: 6.0097. Min Act: -0.1700
Data Index: 3225565 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0722. Min Range: -6.0722
Max Act: 5.9785. Min Act: -0.1700
Data Index: 542301 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0722. Min Range: -6.0722
Max Act: 5.9472. Min Act: -0.1700
Data Index: 3511542 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0722. Min Range: -6.0722
Max Act: 5.9160. Min Act: -0.1700
Data Index: 5131852 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0722. Min Range: -6.0722
Max Act: 5.8535. Min Act: -0.1700
Data Index: 4211603 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0722. Min Range: -6.0722
Max Act: 5.8535. Min Act: -0.1700
Data Index: 4107976 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0722. Min Range: -6.0722
Max Act: 5.8847. Min Act: -0.1700
Data Index: 7366424 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0722. Min Range: -6.0722
Max Act: 5.8847. Min Act: -0.1700
Data Index: 2993881 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0722. Min Range: -6.0722
Max Act: 5.8535. Min Act: -0.1700
Data Index: 43569 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0722. Min Range: -6.0722
Max Act: 5.8847. Min Act: -0.1700
Data Index: 948729 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0722. Min Range: -6.0722
Max Act: 5.7910. Min Act: -0.1700
Data Index: 6876009 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0722. Min Range: -6.0722
Max Act: 5.8222. Min Act: -0.1700
Data Index: 6904007 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0722. Min Range: -6.0722
Max Act: 5.8222. Min Act: -0.1700
Data Index: 609133 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0722. Min Range: -6.0722
Max Act: 5.8222. Min Act: -0.1700
Data Index: 7113942 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0722. Min Range: -6.0722
Max Act: 5.7910. Min Act: -0.1700
Data Index: 4950329 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0722. Min Range: -6.0722
Max Act: 5.7910. Min Act: -0.1700
Data Index: 154929 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0722. Min Range: -6.0722
Max Act: 5.8222. Min Act: -0.1700
Data Index: 334036 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0722. Min Range: -6.0722
Max Act: 5.7910. Min Act: -0.1700
Data Index: 6493601 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19