Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2712 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8670. Min Range: -3.8670
Max Act: 3.8670. Min Act: -0.1700
Data Index: 7212382 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8670. Min Range: -3.8670
Max Act: 3.8670. Min Act: -0.1700
Data Index: 4518303 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8670. Min Range: -3.8670
Max Act: 3.8670. Min Act: -0.1700
Data Index: 624310 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8670. Min Range: -3.8670
Max Act: 3.8670. Min Act: -0.1700
Data Index: 4072081 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8670. Min Range: -3.8670
Max Act: 3.8670. Min Act: -0.1700
Data Index: 2861694 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8670. Min Range: -3.8670
Max Act: 3.8357. Min Act: -0.1700
Data Index: 6570336 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8670. Min Range: -3.8670
Max Act: 3.8357. Min Act: -0.1700
Data Index: 3269920 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8670. Min Range: -3.8670
Max Act: 3.8357. Min Act: -0.1700
Data Index: 1892837 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8670. Min Range: -3.8670
Max Act: 3.8357. Min Act: -0.1700
Data Index: 6126831 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8670. Min Range: -3.8670
Max Act: 3.8357. Min Act: -0.1700
Data Index: 8826924 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8670. Min Range: -3.8670
Max Act: 3.8357. Min Act: -0.1700
Data Index: 8094964 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8670. Min Range: -3.8670
Max Act: 3.8357. Min Act: -0.1700
Data Index: 1425809 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8670. Min Range: -3.8670
Max Act: 3.8357. Min Act: -0.1700
Data Index: 5243034 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8670. Min Range: -3.8670
Max Act: 3.8357. Min Act: -0.1700
Data Index: 7773913 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8670. Min Range: -3.8670
Max Act: 3.8357. Min Act: -0.1700
Data Index: 7281918 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8670. Min Range: -3.8670
Max Act: 3.8045. Min Act: -0.1700
Data Index: 3902133 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8670. Min Range: -3.8670
Max Act: 3.8045. Min Act: -0.1700
Data Index: 2316807 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8670. Min Range: -3.8670
Max Act: 3.8045. Min Act: -0.1700
Data Index: 756724 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8670. Min Range: -3.8670
Max Act: 3.8045. Min Act: -0.1700
Data Index: 1896964 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8670. Min Range: -3.8670
Max Act: 3.8357. Min Act: -0.1700
Data Index: 4195760 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19