Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5315 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7889. Min Range: -6.7889
Max Act: 6.7889. Min Act: -0.1700
Data Index: 2349102 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7889. Min Range: -6.7889
Max Act: 6.1951. Min Act: -0.1700
Data Index: 3679123 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7889. Min Range: -6.7889
Max Act: 6.1639. Min Act: -0.1700
Data Index: 1790055 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7889. Min Range: -6.7889
Max Act: 6.0389. Min Act: -0.1700
Data Index: 6926970 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7889. Min Range: -6.7889
Max Act: 6.0389. Min Act: -0.1700
Data Index: 5355796 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7889. Min Range: -6.7889
Max Act: 6.0076. Min Act: -0.1700
Data Index: 4271278 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7889. Min Range: -6.7889
Max Act: 5.9764. Min Act: -0.1700
Data Index: 1352563 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7889. Min Range: -6.7889
Max Act: 5.9764. Min Act: -0.1700
Data Index: 177907 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7889. Min Range: -6.7889
Max Act: 5.9764. Min Act: -0.1700
Data Index: 2525779 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7889. Min Range: -6.7889
Max Act: 5.9139. Min Act: -0.1700
Data Index: 6762862 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7889. Min Range: -6.7889
Max Act: 5.9451. Min Act: -0.1700
Data Index: 4193777 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7889. Min Range: -6.7889
Max Act: 5.9139. Min Act: -0.1700
Data Index: 4008563 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7889. Min Range: -6.7889
Max Act: 5.8826. Min Act: -0.1700
Data Index: 1099908 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7889. Min Range: -6.7889
Max Act: 5.8826. Min Act: -0.1700
Data Index: 8221810 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7889. Min Range: -6.7889
Max Act: 5.8826. Min Act: -0.1700
Data Index: 5854340 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7889. Min Range: -6.7889
Max Act: 5.8201. Min Act: -0.1700
Data Index: 3251421 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7889. Min Range: -6.7889
Max Act: 5.8201. Min Act: -0.1700
Data Index: 6717782 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7889. Min Range: -6.7889
Max Act: 5.7889. Min Act: -0.1700
Data Index: 909037 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7889. Min Range: -6.7889
Max Act: 5.7889. Min Act: -0.1700
Data Index: 4884276 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7889. Min Range: -6.7889
Max Act: 5.7576. Min Act: -0.1700
Data Index: 6252192 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #19