Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5739 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.9619. Min Act: -0.1700
Data Index: 7764875 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.5557. Min Act: -0.1700
Data Index: 3452003 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.5557. Min Act: -0.1700
Data Index: 8685147 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.5557. Min Act: -0.1700
Data Index: 728606 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.5244. Min Act: -0.1700
Data Index: 8333870 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.4307. Min Act: -0.1700
Data Index: 6108833 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.4307. Min Act: -0.1700
Data Index: 4763269 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.3994. Min Act: -0.1700
Data Index: 1497062 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.3682. Min Act: -0.1700
Data Index: 4954194 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.3682. Min Act: -0.1700
Data Index: 1494117 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.3682. Min Act: -0.1700
Data Index: 8211012 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.3057. Min Act: -0.1700
Data Index: 2769655 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.3682. Min Act: -0.1700
Data Index: 4213218 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.3369. Min Act: -0.1700
Data Index: 8121429 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.3057. Min Act: -0.1700
Data Index: 5006883 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.3057. Min Act: -0.1700
Data Index: 4205736 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.3057. Min Act: -0.1700
Data Index: 80010 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.2432. Min Act: -0.1700
Data Index: 7095041 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.2744. Min Act: -0.1700
Data Index: 8137644 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9619. Min Range: -6.9619
Max Act: 6.2744. Min Act: -0.1700
Data Index: 2514348 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19