Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2855 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.7500. Min Act: -0.1700
Data Index: 6900323 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.7187. Min Act: -0.1700
Data Index: 8362007 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.6562. Min Act: -0.1700
Data Index: 6656899 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.6250. Min Act: -0.1700
Data Index: 1054572 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.6562. Min Act: -0.1700
Data Index: 7811047 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.6250. Min Act: -0.1700
Data Index: 6737593 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.5000. Min Act: -0.1700
Data Index: 5154184 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.5000. Min Act: -0.1700
Data Index: 694730 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.5000. Min Act: -0.1700
Data Index: 8340116 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.4687. Min Act: -0.1700
Data Index: 6748253 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.5000. Min Act: -0.1700
Data Index: 7630824 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.4687. Min Act: -0.1700
Data Index: 6221159 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.5000. Min Act: -0.1700
Data Index: 7342143 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.5000. Min Act: -0.1700
Data Index: 3591064 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.4687. Min Act: -0.1700
Data Index: 4297890 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.4062. Min Act: -0.1700
Data Index: 859410 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.4375. Min Act: -0.1700
Data Index: 1818157 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.4062. Min Act: -0.1700
Data Index: 2068048 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.4375. Min Act: -0.1700
Data Index: 7630823 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.4062. Min Act: -0.1700
Data Index: 6778966 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19