Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 916 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3672. Min Range: -4.3672
Max Act: 4.3672. Min Act: -0.1700
Data Index: 1233144 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3672. Min Range: -4.3672
Max Act: 4.3672. Min Act: -0.1700
Data Index: 1572980 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3672. Min Range: -4.3672
Max Act: 4.3359. Min Act: -0.1700
Data Index: 8326277 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3672. Min Range: -4.3672
Max Act: 4.3359. Min Act: -0.1700
Data Index: 6657748 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3672. Min Range: -4.3672
Max Act: 4.3047. Min Act: -0.1700
Data Index: 8659370 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3672. Min Range: -4.3672
Max Act: 4.3047. Min Act: -0.1700
Data Index: 4800188 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3672. Min Range: -4.3672
Max Act: 4.3047. Min Act: -0.1700
Data Index: 5150270 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3672. Min Range: -4.3672
Max Act: 4.3047. Min Act: -0.1700
Data Index: 3424980 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3672. Min Range: -4.3672
Max Act: 4.2734. Min Act: -0.1700
Data Index: 3780438 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3672. Min Range: -4.3672
Max Act: 4.2734. Min Act: -0.1700
Data Index: 298903 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3672. Min Range: -4.3672
Max Act: 4.2734. Min Act: -0.1700
Data Index: 255438 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3672. Min Range: -4.3672
Max Act: 4.2734. Min Act: -0.1700
Data Index: 1917843 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3672. Min Range: -4.3672
Max Act: 4.2734. Min Act: -0.1700
Data Index: 1660839 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3672. Min Range: -4.3672
Max Act: 4.2422. Min Act: -0.1700
Data Index: 4350241 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3672. Min Range: -4.3672
Max Act: 4.2422. Min Act: -0.1700
Data Index: 8279287 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3672. Min Range: -4.3672
Max Act: 4.2422. Min Act: -0.1700
Data Index: 260665 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3672. Min Range: -4.3672
Max Act: 4.2422. Min Act: -0.1700
Data Index: 7627011 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3672. Min Range: -4.3672
Max Act: 4.2109. Min Act: -0.1700
Data Index: 5437723 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3672. Min Range: -4.3672
Max Act: 4.2109. Min Act: -0.1700
Data Index: 3376197 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3672. Min Range: -4.3672
Max Act: 4.2422. Min Act: -0.1700
Data Index: 4234886 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19