Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1664 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7150. Min Range: -4.7150
Max Act: 4.7150. Min Act: -0.1700
Data Index: 4910488 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7150. Min Range: -4.7150
Max Act: 4.5900. Min Act: -0.1700
Data Index: 903981 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7150. Min Range: -4.7150
Max Act: 4.5275. Min Act: -0.1700
Data Index: 6230015 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7150. Min Range: -4.7150
Max Act: 4.4962. Min Act: -0.1700
Data Index: 5544163 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7150. Min Range: -4.7150
Max Act: 4.4337. Min Act: -0.1700
Data Index: 2671269 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7150. Min Range: -4.7150
Max Act: 4.4025. Min Act: -0.1700
Data Index: 8229370 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7150. Min Range: -4.7150
Max Act: 4.4337. Min Act: -0.1700
Data Index: 6615214 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7150. Min Range: -4.7150
Max Act: 4.4025. Min Act: -0.1700
Data Index: 1000205 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7150. Min Range: -4.7150
Max Act: 4.4025. Min Act: -0.1700
Data Index: 715445 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7150. Min Range: -4.7150
Max Act: 4.4025. Min Act: -0.1700
Data Index: 2326726 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7150. Min Range: -4.7150
Max Act: 4.3712. Min Act: -0.1700
Data Index: 5426671 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7150. Min Range: -4.7150
Max Act: 4.3712. Min Act: -0.1700
Data Index: 391472 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7150. Min Range: -4.7150
Max Act: 4.3400. Min Act: -0.1700
Data Index: 1982233 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7150. Min Range: -4.7150
Max Act: 4.3087. Min Act: -0.1700
Data Index: 602930 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7150. Min Range: -4.7150
Max Act: 4.3087. Min Act: -0.1700
Data Index: 81298 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7150. Min Range: -4.7150
Max Act: 4.3087. Min Act: -0.1700
Data Index: 8612184 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7150. Min Range: -4.7150
Max Act: 4.2775. Min Act: -0.1700
Data Index: 64775 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7150. Min Range: -4.7150
Max Act: 4.2775. Min Act: -0.1700
Data Index: 1868566 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7150. Min Range: -4.7150
Max Act: 4.2775. Min Act: -0.1700
Data Index: 102788 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7150. Min Range: -4.7150
Max Act: 4.2462. Min Act: -0.1700
Data Index: 2815871 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #19