Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2642 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.9147. Min Range: -1.9147
Max Act: 1.9147. Min Act: -0.1700
Data Index: 7836414 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9147. Min Range: -1.9147
Max Act: 1.8977. Min Act: -0.1700
Data Index: 5682736 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9147. Min Range: -1.9147
Max Act: 1.8892. Min Act: -0.1700
Data Index: 405010 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9147. Min Range: -1.9147
Max Act: 1.8806. Min Act: -0.1700
Data Index: 8733685 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9147. Min Range: -1.9147
Max Act: 1.8721. Min Act: -0.1700
Data Index: 2684394 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9147. Min Range: -1.9147
Max Act: 1.8550. Min Act: -0.1700
Data Index: 4871395 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9147. Min Range: -1.9147
Max Act: 1.8464. Min Act: -0.1700
Data Index: 6216140 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9147. Min Range: -1.9147
Max Act: 1.8378. Min Act: -0.1700
Data Index: 6175456 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9147. Min Range: -1.9147
Max Act: 1.8035. Min Act: -0.1700
Data Index: 8459742 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9147. Min Range: -1.9147
Max Act: 1.7949. Min Act: -0.1700
Data Index: 8493524 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9147. Min Range: -1.9147
Max Act: 1.8121. Min Act: -0.1700
Data Index: 3768932 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9147. Min Range: -1.9147
Max Act: 1.8035. Min Act: -0.1700
Data Index: 2876623 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9147. Min Range: -1.9147
Max Act: 1.7863. Min Act: -0.1700
Data Index: 7911169 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9147. Min Range: -1.9147
Max Act: 1.7949. Min Act: -0.1700
Data Index: 3514049 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9147. Min Range: -1.9147
Max Act: 1.7776. Min Act: -0.1698
Data Index: 8230114 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9147. Min Range: -1.9147
Max Act: 1.7863. Min Act: -0.1700
Data Index: 4954080 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9147. Min Range: -1.9147
Max Act: 1.7863. Min Act: -0.1698
Data Index: 8199832 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9147. Min Range: -1.9147
Max Act: 1.7776. Min Act: -0.1700
Data Index: 6072273 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9147. Min Range: -1.9147
Max Act: 1.7863. Min Act: -0.1700
Data Index: 5775728 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9147. Min Range: -1.9147
Max Act: 1.7776. Min Act: -0.1700
Data Index: 7363404 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19