Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3566 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9434. Min Range: -6.9434
Max Act: 6.9434. Min Act: -0.1700
Data Index: 256919 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9434. Min Range: -6.9434
Max Act: 6.9434. Min Act: -0.1700
Data Index: 5488462 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9434. Min Range: -6.9434
Max Act: 6.9122. Min Act: -0.1700
Data Index: 4573319 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9434. Min Range: -6.9434
Max Act: 6.8809. Min Act: -0.1700
Data Index: 4139511 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9434. Min Range: -6.9434
Max Act: 6.8497. Min Act: -0.1700
Data Index: 7962609 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9434. Min Range: -6.9434
Max Act: 6.8497. Min Act: -0.1700
Data Index: 1546369 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9434. Min Range: -6.9434
Max Act: 6.8497. Min Act: -0.1700
Data Index: 7071789 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9434. Min Range: -6.9434
Max Act: 6.8497. Min Act: -0.1700
Data Index: 7381558 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9434. Min Range: -6.9434
Max Act: 6.8184. Min Act: -0.1700
Data Index: 2700469 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9434. Min Range: -6.9434
Max Act: 6.8184. Min Act: -0.1700
Data Index: 8596863 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9434. Min Range: -6.9434
Max Act: 6.7872. Min Act: -0.1700
Data Index: 2442430 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9434. Min Range: -6.9434
Max Act: 6.7872. Min Act: -0.1700
Data Index: 2659310 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9434. Min Range: -6.9434
Max Act: 6.7872. Min Act: -0.1700
Data Index: 1371441 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9434. Min Range: -6.9434
Max Act: 6.7872. Min Act: -0.1700
Data Index: 1061695 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9434. Min Range: -6.9434
Max Act: 6.7872. Min Act: -0.1700
Data Index: 5506214 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9434. Min Range: -6.9434
Max Act: 6.7559. Min Act: -0.1700
Data Index: 1180946 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9434. Min Range: -6.9434
Max Act: 6.7559. Min Act: -0.1700
Data Index: 2827829 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9434. Min Range: -6.9434
Max Act: 6.7872. Min Act: -0.1700
Data Index: 1973559 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9434. Min Range: -6.9434
Max Act: 6.7872. Min Act: -0.1700
Data Index: 5506445 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9434. Min Range: -6.9434
Max Act: 6.6934. Min Act: -0.1700
Data Index: 3406373 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19