Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5277 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.5619. Min Act: -0.1700
Data Index: 5192515 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.4053. Min Act: -0.1700
Data Index: 1210681 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.4053. Min Act: -0.1700
Data Index: 4565752 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.3739. Min Act: -0.1700
Data Index: 2516276 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.3112. Min Act: -0.1700
Data Index: 2251181 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.2955. Min Act: -0.1700
Data Index: 2396878 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.2955. Min Act: -0.1700
Data Index: 1219869 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.2798. Min Act: -0.1700
Data Index: 6448918 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.2326. Min Act: -0.1700
Data Index: 3089129 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.2169. Min Act: -0.1700
Data Index: 5147607 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.2012. Min Act: -0.1700
Data Index: 8559673 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.2012. Min Act: -0.1700
Data Index: 5288386 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.2012. Min Act: -0.1700
Data Index: 4776012 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.1855. Min Act: -0.1700
Data Index: 2115087 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.1855. Min Act: -0.1700
Data Index: 4421498 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.1697. Min Act: -0.1700
Data Index: 5438226 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.1697. Min Act: -0.1700
Data Index: 3265684 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.1697. Min Act: -0.1700
Data Index: 4879869 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.1697. Min Act: -0.1700
Data Index: 6269868 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5619. Min Range: -3.5619
Max Act: 3.1697. Min Act: -0.1700
Data Index: 2115089 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19