Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2037 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5134. Min Range: -6.5134
Max Act: 6.5134. Min Act: -0.1700
Data Index: 6705860 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5134. Min Range: -6.5134
Max Act: 6.1072. Min Act: -0.1700
Data Index: 7507621 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5134. Min Range: -6.5134
Max Act: 6.0447. Min Act: -0.1700
Data Index: 4274660 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5134. Min Range: -6.5134
Max Act: 5.9822. Min Act: -0.1700
Data Index: 573756 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5134. Min Range: -6.5134
Max Act: 5.9509. Min Act: -0.1700
Data Index: 8389574 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5134. Min Range: -6.5134
Max Act: 5.8884. Min Act: -0.1700
Data Index: 2476163 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5134. Min Range: -6.5134
Max Act: 5.8884. Min Act: -0.1700
Data Index: 3877603 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5134. Min Range: -6.5134
Max Act: 5.8572. Min Act: -0.1700
Data Index: 7052535 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5134. Min Range: -6.5134
Max Act: 5.8259. Min Act: -0.1700
Data Index: 6389547 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5134. Min Range: -6.5134
Max Act: 5.7947. Min Act: -0.1700
Data Index: 5247516 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5134. Min Range: -6.5134
Max Act: 5.8259. Min Act: -0.1700
Data Index: 8431849 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5134. Min Range: -6.5134
Max Act: 5.7947. Min Act: -0.1700
Data Index: 1066573 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5134. Min Range: -6.5134
Max Act: 5.8259. Min Act: -0.1700
Data Index: 743471 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5134. Min Range: -6.5134
Max Act: 5.8259. Min Act: -0.1700
Data Index: 5276892 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5134. Min Range: -6.5134
Max Act: 5.7947. Min Act: -0.1700
Data Index: 7115135 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5134. Min Range: -6.5134
Max Act: 5.7634. Min Act: -0.1700
Data Index: 4259912 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5134. Min Range: -6.5134
Max Act: 5.7634. Min Act: -0.1700
Data Index: 7719037 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5134. Min Range: -6.5134
Max Act: 5.7322. Min Act: -0.1700
Data Index: 6267536 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5134. Min Range: -6.5134
Max Act: 5.7322. Min Act: -0.1700
Data Index: 1507556 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5134. Min Range: -6.5134
Max Act: 5.7322. Min Act: -0.1700
Data Index: 7539938 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19