Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3255 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8591. Min Range: -8.8591
Max Act: 8.8591. Min Act: -0.1700
Data Index: 2461676 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8591. Min Range: -8.8591
Max Act: 8.8591. Min Act: -0.1700
Data Index: 786546 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8591. Min Range: -8.8591
Max Act: 8.6716. Min Act: -0.1700
Data Index: 180137 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8591. Min Range: -8.8591
Max Act: 8.6716. Min Act: -0.1700
Data Index: 5505395 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8591. Min Range: -8.8591
Max Act: 8.5466. Min Act: -0.1700
Data Index: 4237264 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8591. Min Range: -8.8591
Max Act: 8.6091. Min Act: -0.1700
Data Index: 8578965 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8591. Min Range: -8.8591
Max Act: 8.4841. Min Act: -0.1700
Data Index: 7909885 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8591. Min Range: -8.8591
Max Act: 8.4841. Min Act: -0.1698
Data Index: 7608327 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8591. Min Range: -8.8591
Max Act: 8.3591. Min Act: -0.1700
Data Index: 7909416 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8591. Min Range: -8.8591
Max Act: 8.3278. Min Act: -0.1700
Data Index: 8076806 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8591. Min Range: -8.8591
Max Act: 8.3278. Min Act: -0.1700
Data Index: 7303768 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8591. Min Range: -8.8591
Max Act: 8.3278. Min Act: -0.1700
Data Index: 5052119 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8591. Min Range: -8.8591
Max Act: 8.2653. Min Act: -0.1700
Data Index: 5279015 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8591. Min Range: -8.8591
Max Act: 8.2341. Min Act: -0.1700
Data Index: 7807281 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8591. Min Range: -8.8591
Max Act: 8.2341. Min Act: -0.1700
Data Index: 8300374 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8591. Min Range: -8.8591
Max Act: 8.2341. Min Act: -0.1700
Data Index: 479707 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8591. Min Range: -8.8591
Max Act: 8.2028. Min Act: -0.1700
Data Index: 232838 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8591. Min Range: -8.8591
Max Act: 8.1716. Min Act: -0.1700
Data Index: 727960 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8591. Min Range: -8.8591
Max Act: 8.1091. Min Act: -0.1700
Data Index: 7167136 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8591. Min Range: -8.8591
Max Act: 8.1403. Min Act: -0.1700
Data Index: 1243017 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19