Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2104 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.8831. Min Act: -0.1700
Data Index: 4073385 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.7580. Min Act: -0.1700
Data Index: 5530770 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.7580. Min Act: -0.1700
Data Index: 3587990 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.7267. Min Act: -0.1700
Data Index: 2920479 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.7580. Min Act: -0.1700
Data Index: 7504117 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.7267. Min Act: -0.1700
Data Index: 6224107 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.7267. Min Act: -0.1700
Data Index: 300839 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.6955. Min Act: -0.1700
Data Index: 2889111 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.6955. Min Act: -0.1700
Data Index: 8662173 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.6955. Min Act: -0.1700
Data Index: 1675324 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.6955. Min Act: -0.1700
Data Index: 5957255 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.6955. Min Act: -0.1700
Data Index: 4041803 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.6955. Min Act: -0.1700
Data Index: 5306544 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.6955. Min Act: -0.1700
Data Index: 1248995 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.6955. Min Act: -0.1700
Data Index: 1797773 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.6329. Min Act: -0.1700
Data Index: 3942249 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.6642. Min Act: -0.1700
Data Index: 3980082 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.6642. Min Act: -0.1700
Data Index: 3999221 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.6642. Min Act: -0.1698
Data Index: 4150853 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.6642. Min Act: -0.1700
Data Index: 4178698 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19