Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5155 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8541. Min Range: -2.8541
Max Act: 2.8541. Min Act: -0.1700
Data Index: 3088776 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8541. Min Range: -2.8541
Max Act: 2.8541. Min Act: -0.1700
Data Index: 3088777 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8541. Min Range: -2.8541
Max Act: 2.7905. Min Act: -0.1700
Data Index: 4704974 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8541. Min Range: -2.8541
Max Act: 2.7905. Min Act: -0.1700
Data Index: 8481547 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8541. Min Range: -2.8541
Max Act: 2.7745. Min Act: -0.1700
Data Index: 6232033 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8541. Min Range: -2.8541
Max Act: 2.7426. Min Act: -0.1700
Data Index: 3268596 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8541. Min Range: -2.8541
Max Act: 2.7426. Min Act: -0.1700
Data Index: 3966382 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8541. Min Range: -2.8541
Max Act: 2.7426. Min Act: -0.1700
Data Index: 5855964 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8541. Min Range: -2.8541
Max Act: 2.7106. Min Act: -0.1700
Data Index: 7163713 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8541. Min Range: -2.8541
Max Act: 2.7106. Min Act: -0.1700
Data Index: 4828308 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8541. Min Range: -2.8541
Max Act: 2.7266. Min Act: -0.1700
Data Index: 941550 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8541. Min Range: -2.8541
Max Act: 2.7106. Min Act: -0.1700
Data Index: 1843615 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8541. Min Range: -2.8541
Max Act: 2.6626. Min Act: -0.1700
Data Index: 1175188 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8541. Min Range: -2.8541
Max Act: 2.6786. Min Act: -0.1700
Data Index: 1491783 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8541. Min Range: -2.8541
Max Act: 2.6786. Min Act: -0.1700
Data Index: 1799456 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8541. Min Range: -2.8541
Max Act: 2.6626. Min Act: -0.1700
Data Index: 7265731 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8541. Min Range: -2.8541
Max Act: 2.6466. Min Act: -0.1700
Data Index: 1771333 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8541. Min Range: -2.8541
Max Act: 2.6626. Min Act: -0.1700
Data Index: 5136747 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8541. Min Range: -2.8541
Max Act: 2.6626. Min Act: -0.1700
Data Index: 3918690 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8541. Min Range: -2.8541
Max Act: 2.6466. Min Act: -0.1700
Data Index: 25043 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #19