Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 650 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9981. Min Range: -3.9981
Max Act: 3.9981. Min Act: -0.1700
Data Index: 8704665 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9981. Min Range: -3.9981
Max Act: 3.9669. Min Act: -0.1700
Data Index: 2170813 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9981. Min Range: -3.9981
Max Act: 3.9669. Min Act: -0.1700
Data Index: 96614 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9981. Min Range: -3.9981
Max Act: 3.8731. Min Act: -0.1700
Data Index: 2465846 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9981. Min Range: -3.9981
Max Act: 3.8106. Min Act: -0.1700
Data Index: 366456 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9981. Min Range: -3.9981
Max Act: 3.7793. Min Act: -0.1700
Data Index: 4589164 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9981. Min Range: -3.9981
Max Act: 3.7793. Min Act: -0.1700
Data Index: 6192501 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9981. Min Range: -3.9981
Max Act: 3.7793. Min Act: -0.1700
Data Index: 968203 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9981. Min Range: -3.9981
Max Act: 3.7793. Min Act: -0.1700
Data Index: 4837941 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9981. Min Range: -3.9981
Max Act: 3.7793. Min Act: -0.1700
Data Index: 3148411 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9981. Min Range: -3.9981
Max Act: 3.7480. Min Act: -0.1700
Data Index: 5059098 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9981. Min Range: -3.9981
Max Act: 3.7480. Min Act: -0.1700
Data Index: 1642437 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9981. Min Range: -3.9981
Max Act: 3.7480. Min Act: -0.1700
Data Index: 830973 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9981. Min Range: -3.9981
Max Act: 3.7167. Min Act: -0.1700
Data Index: 6816506 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9981. Min Range: -3.9981
Max Act: 3.7793. Min Act: -0.1700
Data Index: 6048761 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9981. Min Range: -3.9981
Max Act: 3.7167. Min Act: -0.1700
Data Index: 8100897 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9981. Min Range: -3.9981
Max Act: 3.7167. Min Act: -0.1700
Data Index: 8378564 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9981. Min Range: -3.9981
Max Act: 3.7167. Min Act: -0.1700
Data Index: 928747 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9981. Min Range: -3.9981
Max Act: 3.6854. Min Act: -0.1700
Data Index: 8575036 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9981. Min Range: -3.9981
Max Act: 3.7480. Min Act: -0.1700
Data Index: 6480396 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19