Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4482 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7026. Min Range: -5.7026
Max Act: 5.7026. Min Act: -0.1700
Data Index: 7644047 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7026. Min Range: -5.7026
Max Act: 5.6714. Min Act: -0.1699
Data Index: 3554981 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7026. Min Range: -5.7026
Max Act: 5.6401. Min Act: -0.1700
Data Index: 4475635 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7026. Min Range: -5.7026
Max Act: 5.6401. Min Act: -0.1700
Data Index: 1610134 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7026. Min Range: -5.7026
Max Act: 5.6401. Min Act: -0.1700
Data Index: 175565 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7026. Min Range: -5.7026
Max Act: 5.6089. Min Act: -0.1700
Data Index: 8753604 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7026. Min Range: -5.7026
Max Act: 5.5776. Min Act: -0.1700
Data Index: 1068041 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7026. Min Range: -5.7026
Max Act: 5.5776. Min Act: -0.1700
Data Index: 3776043 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7026. Min Range: -5.7026
Max Act: 5.6089. Min Act: -0.1700
Data Index: 8812706 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7026. Min Range: -5.7026
Max Act: 5.5776. Min Act: -0.1700
Data Index: 3087082 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7026. Min Range: -5.7026
Max Act: 5.5776. Min Act: -0.1700
Data Index: 6257925 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7026. Min Range: -5.7026
Max Act: 5.5776. Min Act: -0.1700
Data Index: 5502659 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7026. Min Range: -5.7026
Max Act: 5.5464. Min Act: -0.1700
Data Index: 4132657 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7026. Min Range: -5.7026
Max Act: 5.5464. Min Act: -0.1700
Data Index: 2965866 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7026. Min Range: -5.7026
Max Act: 5.5464. Min Act: -0.1700
Data Index: 3085464 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7026. Min Range: -5.7026
Max Act: 5.5464. Min Act: -0.1700
Data Index: 1018058 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7026. Min Range: -5.7026
Max Act: 5.5464. Min Act: -0.1700
Data Index: 5026988 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7026. Min Range: -5.7026
Max Act: 5.5464. Min Act: -0.1700
Data Index: 6880843 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7026. Min Range: -5.7026
Max Act: 5.5464. Min Act: -0.1700
Data Index: 525322 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7026. Min Range: -5.7026
Max Act: 5.5464. Min Act: -0.1700
Data Index: 3488381 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #19