Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4201 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7007. Min Range: -5.7007
Max Act: 5.7007. Min Act: -0.1700
Data Index: 7633413 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7007. Min Range: -5.7007
Max Act: 5.6382. Min Act: -0.1700
Data Index: 7345128 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7007. Min Range: -5.7007
Max Act: 5.6070. Min Act: -0.1700
Data Index: 5589164 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7007. Min Range: -5.7007
Max Act: 5.5757. Min Act: -0.1700
Data Index: 3461903 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7007. Min Range: -5.7007
Max Act: 5.5445. Min Act: -0.1700
Data Index: 2149302 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7007. Min Range: -5.7007
Max Act: 5.5445. Min Act: -0.1700
Data Index: 8608599 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7007. Min Range: -5.7007
Max Act: 5.5132. Min Act: -0.1700
Data Index: 451695 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7007. Min Range: -5.7007
Max Act: 5.5132. Min Act: -0.1700
Data Index: 5174846 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7007. Min Range: -5.7007
Max Act: 5.5445. Min Act: -0.1700
Data Index: 2818826 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7007. Min Range: -5.7007
Max Act: 5.4820. Min Act: -0.1700
Data Index: 1613095 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7007. Min Range: -5.7007
Max Act: 5.4195. Min Act: -0.1700
Data Index: 4710238 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7007. Min Range: -5.7007
Max Act: 5.4195. Min Act: -0.1700
Data Index: 350787 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7007. Min Range: -5.7007
Max Act: 5.4195. Min Act: -0.1700
Data Index: 4819373 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7007. Min Range: -5.7007
Max Act: 5.4195. Min Act: -0.1700
Data Index: 5228280 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7007. Min Range: -5.7007
Max Act: 5.4195. Min Act: -0.1700
Data Index: 6060116 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7007. Min Range: -5.7007
Max Act: 5.4195. Min Act: -0.1700
Data Index: 4819381 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7007. Min Range: -5.7007
Max Act: 5.3882. Min Act: -0.1700
Data Index: 6888592 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7007. Min Range: -5.7007
Max Act: 5.3882. Min Act: -0.1700
Data Index: 2984077 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7007. Min Range: -5.7007
Max Act: 5.3882. Min Act: -0.1700
Data Index: 2919640 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7007. Min Range: -5.7007
Max Act: 5.3570. Min Act: -0.1700
Data Index: 4423611 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #19