Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4770 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0182. Min Range: -7.0182
Max Act: 7.0182. Min Act: -0.1700
Data Index: 5009696 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0182. Min Range: -7.0182
Max Act: 6.9557. Min Act: -0.1700
Data Index: 3198082 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0182. Min Range: -7.0182
Max Act: 6.8620. Min Act: -0.1700
Data Index: 6437970 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0182. Min Range: -7.0182
Max Act: 6.7995. Min Act: -0.1700
Data Index: 7095740 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0182. Min Range: -7.0182
Max Act: 6.7995. Min Act: -0.1700
Data Index: 5461640 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0182. Min Range: -7.0182
Max Act: 6.7682. Min Act: -0.1700
Data Index: 7123511 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0182. Min Range: -7.0182
Max Act: 6.7370. Min Act: -0.1700
Data Index: 7732625 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0182. Min Range: -7.0182
Max Act: 6.7370. Min Act: -0.1700
Data Index: 1728266 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0182. Min Range: -7.0182
Max Act: 6.7370. Min Act: -0.1700
Data Index: 2748543 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0182. Min Range: -7.0182
Max Act: 6.7057. Min Act: -0.1700
Data Index: 3707616 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0182. Min Range: -7.0182
Max Act: 6.7057. Min Act: -0.1700
Data Index: 4255381 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0182. Min Range: -7.0182
Max Act: 6.7370. Min Act: -0.1700
Data Index: 5188028 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0182. Min Range: -7.0182
Max Act: 6.7370. Min Act: -0.1700
Data Index: 7778200 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0182. Min Range: -7.0182
Max Act: 6.7057. Min Act: -0.1700
Data Index: 291183 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0182. Min Range: -7.0182
Max Act: 6.7057. Min Act: -0.1700
Data Index: 2162747 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0182. Min Range: -7.0182
Max Act: 6.6745. Min Act: -0.1700
Data Index: 5357253 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0182. Min Range: -7.0182
Max Act: 6.7057. Min Act: -0.1700
Data Index: 6877298 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0182. Min Range: -7.0182
Max Act: 6.6745. Min Act: -0.1700
Data Index: 8730944 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0182. Min Range: -7.0182
Max Act: 6.6745. Min Act: -0.1700
Data Index: 1414197 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0182. Min Range: -7.0182
Max Act: 6.6432. Min Act: -0.1700
Data Index: 2154354 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19