Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3069 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6982. Min Range: -3.6982
Max Act: 3.6669. Min Act: -0.1700
Data Index: 3893433 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6982. Min Range: -3.6982
Max Act: 3.6669. Min Act: -0.1700
Data Index: 5039270 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6982. Min Range: -3.6982
Max Act: 3.6982. Min Act: -0.1700
Data Index: 1871092 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6982. Min Range: -3.6982
Max Act: 3.6043. Min Act: -0.1700
Data Index: 1464204 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6982. Min Range: -3.6982
Max Act: 3.5730. Min Act: -0.1700
Data Index: 6484908 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6982. Min Range: -3.6982
Max Act: 3.5730. Min Act: -0.1700
Data Index: 4772112 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6982. Min Range: -3.6982
Max Act: 3.5730. Min Act: -0.1700
Data Index: 5768515 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6982. Min Range: -3.6982
Max Act: 3.5417. Min Act: -0.1700
Data Index: 7039626 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6982. Min Range: -3.6982
Max Act: 3.5417. Min Act: -0.1700
Data Index: 4844698 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6982. Min Range: -3.6982
Max Act: 3.5417. Min Act: -0.1700
Data Index: 5131146 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6982. Min Range: -3.6982
Max Act: 3.5417. Min Act: -0.1700
Data Index: 5253456 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6982. Min Range: -3.6982
Max Act: 3.5417. Min Act: -0.1700
Data Index: 5384954 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6982. Min Range: -3.6982
Max Act: 3.5104. Min Act: -0.1700
Data Index: 2649285 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6982. Min Range: -3.6982
Max Act: 3.5104. Min Act: -0.1700
Data Index: 6315380 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6982. Min Range: -3.6982
Max Act: 3.5104. Min Act: -0.1700
Data Index: 2629607 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6982. Min Range: -3.6982
Max Act: 3.5104. Min Act: -0.1700
Data Index: 1217936 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6982. Min Range: -3.6982
Max Act: 3.5104. Min Act: -0.1700
Data Index: 5358038 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6982. Min Range: -3.6982
Max Act: 3.5104. Min Act: -0.1700
Data Index: 5107567 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6982. Min Range: -3.6982
Max Act: 3.5104. Min Act: -0.1700
Data Index: 1629886 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6982. Min Range: -3.6982
Max Act: 3.5104. Min Act: -0.1700
Data Index: 1487372 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19