Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3501 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1680. Min Range: -6.1680
Max Act: 6.1680. Min Act: -0.1700
Data Index: 8787014 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1680. Min Range: -6.1680
Max Act: 6.1680. Min Act: -0.1700
Data Index: 3718775 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1680. Min Range: -6.1680
Max Act: 6.1055. Min Act: -0.1700
Data Index: 1443278 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1680. Min Range: -6.1680
Max Act: 6.1055. Min Act: -0.1700
Data Index: 4911070 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1680. Min Range: -6.1680
Max Act: 6.1055. Min Act: -0.1700
Data Index: 7510416 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1680. Min Range: -6.1680
Max Act: 6.0742. Min Act: -0.1700
Data Index: 8482238 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1680. Min Range: -6.1680
Max Act: 6.0742. Min Act: -0.1700
Data Index: 350990 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1680. Min Range: -6.1680
Max Act: 6.0742. Min Act: -0.1700
Data Index: 887529 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1680. Min Range: -6.1680
Max Act: 6.0430. Min Act: -0.1700
Data Index: 4198474 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1680. Min Range: -6.1680
Max Act: 5.9805. Min Act: -0.1700
Data Index: 5201982 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1680. Min Range: -6.1680
Max Act: 6.0117. Min Act: -0.1700
Data Index: 8432686 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1680. Min Range: -6.1680
Max Act: 6.0117. Min Act: -0.1700
Data Index: 2945360 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1680. Min Range: -6.1680
Max Act: 5.9492. Min Act: -0.1700
Data Index: 401330 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1680. Min Range: -6.1680
Max Act: 5.9805. Min Act: -0.1700
Data Index: 2104814 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1680. Min Range: -6.1680
Max Act: 5.9492. Min Act: -0.1700
Data Index: 1665223 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1680. Min Range: -6.1680
Max Act: 5.9492. Min Act: -0.1700
Data Index: 7892356 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1680. Min Range: -6.1680
Max Act: 5.9492. Min Act: -0.1700
Data Index: 1879500 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1680. Min Range: -6.1680
Max Act: 5.9180. Min Act: -0.1700
Data Index: 2265667 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1680. Min Range: -6.1680
Max Act: 5.9492. Min Act: -0.1700
Data Index: 1563843 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1680. Min Range: -6.1680
Max Act: 5.9180. Min Act: -0.1700
Data Index: 6145449 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #19