Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5876 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3034. Min Range: -6.3034
Max Act: 6.3034. Min Act: -0.1700
Data Index: 2098776 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3034. Min Range: -6.3034
Max Act: 6.2409. Min Act: -0.1700
Data Index: 8409355 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3034. Min Range: -6.3034
Max Act: 6.2097. Min Act: -0.1700
Data Index: 4145267 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3034. Min Range: -6.3034
Max Act: 5.9909. Min Act: -0.1700
Data Index: 7284270 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3034. Min Range: -6.3034
Max Act: 5.9284. Min Act: -0.1700
Data Index: 1233395 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3034. Min Range: -6.3034
Max Act: 5.8347. Min Act: -0.1700
Data Index: 3080204 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3034. Min Range: -6.3034
Max Act: 5.7722. Min Act: -0.1700
Data Index: 1656448 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3034. Min Range: -6.3034
Max Act: 5.7722. Min Act: -0.1700
Data Index: 1528628 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3034. Min Range: -6.3034
Max Act: 5.8034. Min Act: -0.1700
Data Index: 6037664 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3034. Min Range: -6.3034
Max Act: 5.7722. Min Act: -0.1700
Data Index: 6946825 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3034. Min Range: -6.3034
Max Act: 5.7409. Min Act: -0.1700
Data Index: 4968826 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3034. Min Range: -6.3034
Max Act: 5.6784. Min Act: -0.1700
Data Index: 8648410 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3034. Min Range: -6.3034
Max Act: 5.6784. Min Act: -0.1700
Data Index: 5500770 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3034. Min Range: -6.3034
Max Act: 5.6784. Min Act: -0.1700
Data Index: 3002230 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3034. Min Range: -6.3034
Max Act: 5.6784. Min Act: -0.1700
Data Index: 3740305 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3034. Min Range: -6.3034
Max Act: 5.6159. Min Act: -0.1700
Data Index: 24815 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3034. Min Range: -6.3034
Max Act: 5.6159. Min Act: -0.1700
Data Index: 2487866 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3034. Min Range: -6.3034
Max Act: 5.6159. Min Act: -0.1700
Data Index: 3340636 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3034. Min Range: -6.3034
Max Act: 5.6159. Min Act: -0.1700
Data Index: 5083874 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3034. Min Range: -6.3034
Max Act: 5.6159. Min Act: -0.1700
Data Index: 2108011 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #19