Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3682 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8180. Min Range: -5.8180
Max Act: 5.8180. Min Act: -0.1700
Data Index: 3412294 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8180. Min Range: -5.8180
Max Act: 5.7867. Min Act: -0.1700
Data Index: 2921234 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8180. Min Range: -5.8180
Max Act: 5.7242. Min Act: -0.1700
Data Index: 5879264 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8180. Min Range: -5.8180
Max Act: 5.6930. Min Act: -0.1700
Data Index: 4119861 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8180. Min Range: -5.8180
Max Act: 5.6305. Min Act: -0.1700
Data Index: 7314218 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8180. Min Range: -5.8180
Max Act: 5.5992. Min Act: -0.1700
Data Index: 1195866 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8180. Min Range: -5.8180
Max Act: 5.5992. Min Act: -0.1700
Data Index: 7949800 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8180. Min Range: -5.8180
Max Act: 5.5680. Min Act: -0.1700
Data Index: 2522977 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8180. Min Range: -5.8180
Max Act: 5.5367. Min Act: -0.1700
Data Index: 3788214 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8180. Min Range: -5.8180
Max Act: 5.5367. Min Act: -0.1700
Data Index: 6146741 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8180. Min Range: -5.8180
Max Act: 5.5055. Min Act: -0.1700
Data Index: 748235 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8180. Min Range: -5.8180
Max Act: 5.5055. Min Act: -0.1700
Data Index: 27368 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8180. Min Range: -5.8180
Max Act: 5.5055. Min Act: -0.1700
Data Index: 4140615 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8180. Min Range: -5.8180
Max Act: 5.4742. Min Act: -0.1700
Data Index: 5505168 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8180. Min Range: -5.8180
Max Act: 5.4742. Min Act: -0.1700
Data Index: 920425 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8180. Min Range: -5.8180
Max Act: 5.4742. Min Act: -0.1700
Data Index: 8638982 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8180. Min Range: -5.8180
Max Act: 5.4742. Min Act: -0.1700
Data Index: 7950574 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8180. Min Range: -5.8180
Max Act: 5.4430. Min Act: -0.1700
Data Index: 8207693 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8180. Min Range: -5.8180
Max Act: 5.4430. Min Act: -0.1700
Data Index: 6334509 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8180. Min Range: -5.8180
Max Act: 5.4117. Min Act: -0.1700
Data Index: 17939 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #19