Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1612 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1810. Min Range: -8.1810
Max Act: 8.1810. Min Act: -0.1700
Data Index: 5111203 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1810. Min Range: -8.1810
Max Act: 8.0560. Min Act: -0.1700
Data Index: 4726186 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1810. Min Range: -8.1810
Max Act: 7.9935. Min Act: -0.1700
Data Index: 709907 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1810. Min Range: -8.1810
Max Act: 7.8685. Min Act: -0.1700
Data Index: 4556768 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1810. Min Range: -8.1810
Max Act: 7.8685. Min Act: -0.1700
Data Index: 1730679 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1810. Min Range: -8.1810
Max Act: 7.8060. Min Act: -0.1700
Data Index: 4051476 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1810. Min Range: -8.1810
Max Act: 7.7435. Min Act: -0.1700
Data Index: 663344 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1810. Min Range: -8.1810
Max Act: 7.7435. Min Act: -0.1700
Data Index: 8659831 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1810. Min Range: -8.1810
Max Act: 7.6810. Min Act: -0.1700
Data Index: 5113148 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1810. Min Range: -8.1810
Max Act: 7.6810. Min Act: -0.1700
Data Index: 4696823 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1810. Min Range: -8.1810
Max Act: 7.6185. Min Act: -0.1700
Data Index: 8350772 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1810. Min Range: -8.1810
Max Act: 7.6185. Min Act: -0.1700
Data Index: 3034482 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1810. Min Range: -8.1810
Max Act: 7.6185. Min Act: -0.1700
Data Index: 592437 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1810. Min Range: -8.1810
Max Act: 7.6185. Min Act: -0.1700
Data Index: 3092671 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1810. Min Range: -8.1810
Max Act: 7.6185. Min Act: -0.1700
Data Index: 3525881 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1810. Min Range: -8.1810
Max Act: 7.5873. Min Act: -0.1700
Data Index: 8704912 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1810. Min Range: -8.1810
Max Act: 7.5873. Min Act: -0.1700
Data Index: 7766039 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1810. Min Range: -8.1810
Max Act: 7.5560. Min Act: -0.1700
Data Index: 6937953 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1810. Min Range: -8.1810
Max Act: 7.5248. Min Act: -0.1700
Data Index: 5380896 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1810. Min Range: -8.1810
Max Act: 7.5248. Min Act: -0.1700
Data Index: 2946692 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #19