Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1902 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7073. Min Range: -5.7073
Max Act: 5.7073. Min Act: -0.1700
Data Index: 1565963 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7073. Min Range: -5.7073
Max Act: 5.5823. Min Act: -0.1700
Data Index: 1565959 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7073. Min Range: -5.7073
Max Act: 5.5511. Min Act: -0.1700
Data Index: 3249007 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7073. Min Range: -5.7073
Max Act: 5.5511. Min Act: -0.1700
Data Index: 571296 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7073. Min Range: -5.7073
Max Act: 5.5198. Min Act: -0.1700
Data Index: 7962015 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7073. Min Range: -5.7073
Max Act: 5.5198. Min Act: -0.1700
Data Index: 3376491 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7073. Min Range: -5.7073
Max Act: 5.5198. Min Act: -0.1700
Data Index: 4171308 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7073. Min Range: -5.7073
Max Act: 5.5198. Min Act: -0.1700
Data Index: 2391221 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7073. Min Range: -5.7073
Max Act: 5.5198. Min Act: -0.1698
Data Index: 6269209 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7073. Min Range: -5.7073
Max Act: 5.4886. Min Act: -0.1700
Data Index: 2784728 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7073. Min Range: -5.7073
Max Act: 5.4886. Min Act: -0.1700
Data Index: 8087102 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7073. Min Range: -5.7073
Max Act: 5.4886. Min Act: -0.1700
Data Index: 593084 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7073. Min Range: -5.7073
Max Act: 5.4886. Min Act: -0.1700
Data Index: 6699366 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7073. Min Range: -5.7073
Max Act: 5.4886. Min Act: -0.1700
Data Index: 474767 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7073. Min Range: -5.7073
Max Act: 5.4886. Min Act: -0.1700
Data Index: 1383616 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7073. Min Range: -5.7073
Max Act: 5.4573. Min Act: -0.1700
Data Index: 7032625 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7073. Min Range: -5.7073
Max Act: 5.4573. Min Act: -0.1700
Data Index: 5240634 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7073. Min Range: -5.7073
Max Act: 5.4573. Min Act: -0.1700
Data Index: 3175754 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7073. Min Range: -5.7073
Max Act: 5.4573. Min Act: -0.1700
Data Index: 5044418 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7073. Min Range: -5.7073
Max Act: 5.4573. Min Act: -0.1700
Data Index: 2212012 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19