Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3992 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1903. Min Range: -10.1903
Max Act: 10.1903. Min Act: -0.1700
Data Index: 2255283 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1903. Min Range: -10.1903
Max Act: 9.3153. Min Act: -0.1700
Data Index: 5088891 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1903. Min Range: -10.1903
Max Act: 9.2528. Min Act: -0.1700
Data Index: 2742764 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1903. Min Range: -10.1903
Max Act: 9.1903. Min Act: -0.1700
Data Index: 8554119 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1903. Min Range: -10.1903
Max Act: 9.1903. Min Act: -0.1700
Data Index: 7601220 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1903. Min Range: -10.1903
Max Act: 9.1278. Min Act: -0.1700
Data Index: 5749917 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1903. Min Range: -10.1903
Max Act: 9.1278. Min Act: -0.1700
Data Index: 5559062 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1903. Min Range: -10.1903
Max Act: 9.0653. Min Act: -0.1700
Data Index: 6162116 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1903. Min Range: -10.1903
Max Act: 9.0028. Min Act: -0.1700
Data Index: 727735 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1903. Min Range: -10.1903
Max Act: 9.0028. Min Act: -0.1700
Data Index: 1020040 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1903. Min Range: -10.1903
Max Act: 9.0028. Min Act: -0.1700
Data Index: 6035153 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1903. Min Range: -10.1903
Max Act: 8.9403. Min Act: -0.1700
Data Index: 1913810 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1903. Min Range: -10.1903
Max Act: 8.9403. Min Act: -0.1700
Data Index: 4956892 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1903. Min Range: -10.1903
Max Act: 8.9403. Min Act: -0.1700
Data Index: 4335921 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1903. Min Range: -10.1903
Max Act: 8.9403. Min Act: -0.1700
Data Index: 3040364 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1903. Min Range: -10.1903
Max Act: 8.8778. Min Act: -0.1700
Data Index: 8385819 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1903. Min Range: -10.1903
Max Act: 8.8778. Min Act: -0.1700
Data Index: 2797224 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1903. Min Range: -10.1903
Max Act: 8.8778. Min Act: -0.1700
Data Index: 8742997 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1903. Min Range: -10.1903
Max Act: 8.8778. Min Act: -0.1700
Data Index: 6385096 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1903. Min Range: -10.1903
Max Act: 8.8153. Min Act: -0.1700
Data Index: 6671360 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19