Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3976 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9811. Min Range: -1.9811
Max Act: 1.9811. Min Act: -0.1700
Data Index: 5205359 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9811. Min Range: -1.9811
Max Act: 1.9472. Min Act: -0.1700
Data Index: 631546 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9811. Min Range: -1.9811
Max Act: 1.9046. Min Act: -0.1700
Data Index: 5730803 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9811. Min Range: -1.9811
Max Act: 1.9132. Min Act: -0.1699
Data Index: 3594687 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9811. Min Range: -1.9811
Max Act: 1.8961. Min Act: -0.1682
Data Index: 2993585 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9811. Min Range: -1.9811
Max Act: 1.8961. Min Act: -0.1700
Data Index: 2890192 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9811. Min Range: -1.9811
Max Act: 1.8876. Min Act: -0.1700
Data Index: 31583 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9811. Min Range: -1.9811
Max Act: 1.8961. Min Act: -0.1700
Data Index: 3315800 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9811. Min Range: -1.9811
Max Act: 1.8961. Min Act: -0.1700
Data Index: 706161 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9811. Min Range: -1.9811
Max Act: 1.8876. Min Act: -0.1700
Data Index: 686903 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9811. Min Range: -1.9811
Max Act: 1.8876. Min Act: -0.1696
Data Index: 6906356 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9811. Min Range: -1.9811
Max Act: 1.8790. Min Act: -0.1700
Data Index: 1767959 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9811. Min Range: -1.9811
Max Act: 1.8876. Min Act: -0.1699
Data Index: 5475131 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9811. Min Range: -1.9811
Max Act: 1.8705. Min Act: -0.1700
Data Index: 6540401 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9811. Min Range: -1.9811
Max Act: 1.8790. Min Act: -0.1700
Data Index: 6996935 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9811. Min Range: -1.9811
Max Act: 1.8705. Min Act: -0.1694
Data Index: 5160272 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9811. Min Range: -1.9811
Max Act: 1.8619. Min Act: -0.1696
Data Index: 2586913 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9811. Min Range: -1.9811
Max Act: 1.8619. Min Act: -0.1698
Data Index: 4160309 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9811. Min Range: -1.9811
Max Act: 1.8790. Min Act: -0.1699
Data Index: 6392010 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9811. Min Range: -1.9811
Max Act: 1.8619. Min Act: -0.1700
Data Index: 687458 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19