Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3877 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5455. Min Range: -5.5455
Max Act: 5.5455. Min Act: -0.1700
Data Index: 497441 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5455. Min Range: -5.5455
Max Act: 5.4517. Min Act: -0.1700
Data Index: 4047173 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5455. Min Range: -5.5455
Max Act: 5.2017. Min Act: -0.1700
Data Index: 7642677 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5455. Min Range: -5.5455
Max Act: 5.0767. Min Act: -0.1700
Data Index: 7305681 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5455. Min Range: -5.5455
Max Act: 5.1080. Min Act: -0.1700
Data Index: 4556782 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5455. Min Range: -5.5455
Max Act: 5.0767. Min Act: -0.1700
Data Index: 2845054 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5455. Min Range: -5.5455
Max Act: 5.0455. Min Act: -0.1700
Data Index: 655449 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5455. Min Range: -5.5455
Max Act: 5.0455. Min Act: -0.1700
Data Index: 5174039 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5455. Min Range: -5.5455
Max Act: 5.0455. Min Act: -0.1700
Data Index: 1826451 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5455. Min Range: -5.5455
Max Act: 5.0455. Min Act: -0.1700
Data Index: 1435155 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5455. Min Range: -5.5455
Max Act: 5.0455. Min Act: -0.1700
Data Index: 8466518 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5455. Min Range: -5.5455
Max Act: 4.9517. Min Act: -0.1700
Data Index: 577804 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5455. Min Range: -5.5455
Max Act: 4.9830. Min Act: -0.1700
Data Index: 6728869 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5455. Min Range: -5.5455
Max Act: 4.9517. Min Act: -0.1700
Data Index: 7695904 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5455. Min Range: -5.5455
Max Act: 4.9830. Min Act: -0.1700
Data Index: 3356853 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5455. Min Range: -5.5455
Max Act: 4.9517. Min Act: -0.1700
Data Index: 741422 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5455. Min Range: -5.5455
Max Act: 4.9205. Min Act: -0.1700
Data Index: 4322565 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5455. Min Range: -5.5455
Max Act: 4.8892. Min Act: -0.1700
Data Index: 2864734 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5455. Min Range: -5.5455
Max Act: 4.8892. Min Act: -0.1700
Data Index: 2437787 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5455. Min Range: -5.5455
Max Act: 4.9205. Min Act: -0.1700
Data Index: 6101387 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19