Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3684 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7058. Min Range: -5.7058
Max Act: 5.7058. Min Act: -0.1700
Data Index: 8384423 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7058. Min Range: -5.7058
Max Act: 5.7058. Min Act: -0.1700
Data Index: 1265654 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7058. Min Range: -5.7058
Max Act: 5.6433. Min Act: -0.1700
Data Index: 6914139 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7058. Min Range: -5.7058
Max Act: 5.6120. Min Act: -0.1700
Data Index: 6957116 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7058. Min Range: -5.7058
Max Act: 5.6120. Min Act: -0.1700
Data Index: 400967 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7058. Min Range: -5.7058
Max Act: 5.5495. Min Act: -0.1700
Data Index: 1260328 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7058. Min Range: -5.7058
Max Act: 5.5808. Min Act: -0.1700
Data Index: 1905520 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7058. Min Range: -5.7058
Max Act: 5.5808. Min Act: -0.1700
Data Index: 6689963 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7058. Min Range: -5.7058
Max Act: 5.5495. Min Act: -0.1700
Data Index: 6224656 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7058. Min Range: -5.7058
Max Act: 5.5495. Min Act: -0.1700
Data Index: 8469854 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7058. Min Range: -5.7058
Max Act: 5.5495. Min Act: -0.1700
Data Index: 1265659 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7058. Min Range: -5.7058
Max Act: 5.5183. Min Act: -0.1700
Data Index: 5475416 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7058. Min Range: -5.7058
Max Act: 5.5183. Min Act: -0.1700
Data Index: 6914138 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7058. Min Range: -5.7058
Max Act: 5.5183. Min Act: -0.1700
Data Index: 4769261 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7058. Min Range: -5.7058
Max Act: 5.5183. Min Act: -0.1700
Data Index: 4492721 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7058. Min Range: -5.7058
Max Act: 5.5183. Min Act: -0.1700
Data Index: 7559240 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7058. Min Range: -5.7058
Max Act: 5.4870. Min Act: -0.1700
Data Index: 5475417 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7058. Min Range: -5.7058
Max Act: 5.4870. Min Act: -0.1700
Data Index: 5587862 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7058. Min Range: -5.7058
Max Act: 5.4870. Min Act: -0.1700
Data Index: 7008578 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7058. Min Range: -5.7058
Max Act: 5.4870. Min Act: -0.1700
Data Index: 7598904 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #19