Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4889 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0007. Min Range: -10.0007
Max Act: 10.0007. Min Act: -0.1700
Data Index: 6484270 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0007. Min Range: -10.0007
Max Act: 9.9382. Min Act: -0.1700
Data Index: 4075149 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0007. Min Range: -10.0007
Max Act: 9.7507. Min Act: -0.1700
Data Index: 3117016 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0007. Min Range: -10.0007
Max Act: 9.6882. Min Act: -0.1700
Data Index: 6207815 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0007. Min Range: -10.0007
Max Act: 9.6882. Min Act: -0.1700
Data Index: 5540366 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0007. Min Range: -10.0007
Max Act: 9.6882. Min Act: -0.1700
Data Index: 4484914 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0007. Min Range: -10.0007
Max Act: 9.6882. Min Act: -0.1700
Data Index: 753446 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0007. Min Range: -10.0007
Max Act: 9.6882. Min Act: -0.1700
Data Index: 8514122 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0007. Min Range: -10.0007
Max Act: 9.6257. Min Act: -0.1700
Data Index: 7218952 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0007. Min Range: -10.0007
Max Act: 9.6257. Min Act: -0.1700
Data Index: 6036602 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0007. Min Range: -10.0007
Max Act: 9.5632. Min Act: -0.1700
Data Index: 8296499 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0007. Min Range: -10.0007
Max Act: 9.5632. Min Act: -0.1700
Data Index: 3016083 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0007. Min Range: -10.0007
Max Act: 9.5632. Min Act: -0.1700
Data Index: 4345162 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0007. Min Range: -10.0007
Max Act: 9.5007. Min Act: -0.1700
Data Index: 949439 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0007. Min Range: -10.0007
Max Act: 9.5007. Min Act: -0.1700
Data Index: 6357893 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0007. Min Range: -10.0007
Max Act: 9.5007. Min Act: -0.1700
Data Index: 7818036 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0007. Min Range: -10.0007
Max Act: 9.5632. Min Act: -0.1700
Data Index: 3174299 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0007. Min Range: -10.0007
Max Act: 9.5007. Min Act: -0.1700
Data Index: 3702321 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0007. Min Range: -10.0007
Max Act: 9.4382. Min Act: -0.1700
Data Index: 1949990 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0007. Min Range: -10.0007
Max Act: 9.4382. Min Act: -0.1700
Data Index: 6852790 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19