Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3442 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3896. Min Range: -8.3896
Max Act: 8.3896. Min Act: -0.1700
Data Index: 1650988 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3896. Min Range: -8.3896
Max Act: 8.3271. Min Act: -0.1700
Data Index: 5610975 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3896. Min Range: -8.3896
Max Act: 8.3271. Min Act: -0.1700
Data Index: 5624892 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3896. Min Range: -8.3896
Max Act: 8.2646. Min Act: -0.1700
Data Index: 3680414 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3896. Min Range: -8.3896
Max Act: 8.2646. Min Act: -0.1700
Data Index: 4529882 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3896. Min Range: -8.3896
Max Act: 8.2021. Min Act: -0.1700
Data Index: 6033760 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3896. Min Range: -8.3896
Max Act: 8.2021. Min Act: -0.1700
Data Index: 7276538 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3896. Min Range: -8.3896
Max Act: 8.1396. Min Act: -0.1700
Data Index: 1980663 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3896. Min Range: -8.3896
Max Act: 8.1083. Min Act: -0.1700
Data Index: 727714 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3896. Min Range: -8.3896
Max Act: 8.1083. Min Act: -0.1700
Data Index: 6231838 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3896. Min Range: -8.3896
Max Act: 8.1083. Min Act: -0.1700
Data Index: 4491168 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3896. Min Range: -8.3896
Max Act: 8.0458. Min Act: -0.1700
Data Index: 2605010 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3896. Min Range: -8.3896
Max Act: 8.0458. Min Act: -0.1700
Data Index: 7038831 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3896. Min Range: -8.3896
Max Act: 8.0458. Min Act: -0.1700
Data Index: 5624893 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3896. Min Range: -8.3896
Max Act: 8.0458. Min Act: -0.1700
Data Index: 2463172 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3896. Min Range: -8.3896
Max Act: 8.0458. Min Act: -0.1700
Data Index: 8246515 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3896. Min Range: -8.3896
Max Act: 8.0146. Min Act: -0.1700
Data Index: 4822366 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3896. Min Range: -8.3896
Max Act: 8.0458. Min Act: -0.1700
Data Index: 7857896 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3896. Min Range: -8.3896
Max Act: 8.0146. Min Act: -0.1700
Data Index: 1343966 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3896. Min Range: -8.3896
Max Act: 8.0146. Min Act: -0.1700
Data Index: 6308758 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19