Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 52 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0977. Min Range: -4.0977
Max Act: 4.0977. Min Act: -0.1700
Data Index: 7898271 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0977. Min Range: -4.0977
Max Act: 4.0664. Min Act: -0.1700
Data Index: 1097180 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0977. Min Range: -4.0977
Max Act: 3.9726. Min Act: -0.1700
Data Index: 424609 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0977. Min Range: -4.0977
Max Act: 3.9726. Min Act: -0.1700
Data Index: 2685134 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0977. Min Range: -4.0977
Max Act: 3.9414. Min Act: -0.1700
Data Index: 5232029 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0977. Min Range: -4.0977
Max Act: 3.9414. Min Act: -0.1700
Data Index: 1332385 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0977. Min Range: -4.0977
Max Act: 3.9101. Min Act: -0.1700
Data Index: 3893884 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0977. Min Range: -4.0977
Max Act: 3.9101. Min Act: -0.1700
Data Index: 8101071 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0977. Min Range: -4.0977
Max Act: 3.8788. Min Act: -0.1700
Data Index: 970296 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0977. Min Range: -4.0977
Max Act: 3.8788. Min Act: -0.1700
Data Index: 859041 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0977. Min Range: -4.0977
Max Act: 3.8788. Min Act: -0.1700
Data Index: 2088326 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0977. Min Range: -4.0977
Max Act: 3.8476. Min Act: -0.1700
Data Index: 3873814 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0977. Min Range: -4.0977
Max Act: 3.8476. Min Act: -0.1700
Data Index: 4803421 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0977. Min Range: -4.0977
Max Act: 3.8476. Min Act: -0.1700
Data Index: 3528695 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0977. Min Range: -4.0977
Max Act: 3.8476. Min Act: -0.1700
Data Index: 5171837 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0977. Min Range: -4.0977
Max Act: 3.8476. Min Act: -0.1700
Data Index: 6870957 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0977. Min Range: -4.0977
Max Act: 3.8163. Min Act: -0.1700
Data Index: 1526950 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0977. Min Range: -4.0977
Max Act: 3.8163. Min Act: -0.1700
Data Index: 4178009 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0977. Min Range: -4.0977
Max Act: 3.8163. Min Act: -0.1700
Data Index: 2481911 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0977. Min Range: -4.0977
Max Act: 3.8163. Min Act: -0.1700
Data Index: 5166516 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #19