Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4120 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5376. Min Range: -9.5376
Max Act: 9.5376. Min Act: -0.1700
Data Index: 8170696 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5376. Min Range: -9.5376
Max Act: 9.3501. Min Act: -0.1700
Data Index: 4872311 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5376. Min Range: -9.5376
Max Act: 9.2876. Min Act: -0.1700
Data Index: 2789906 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5376. Min Range: -9.5376
Max Act: 9.2251. Min Act: -0.1700
Data Index: 2846207 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5376. Min Range: -9.5376
Max Act: 9.1626. Min Act: -0.1700
Data Index: 7632958 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5376. Min Range: -9.5376
Max Act: 9.1626. Min Act: -0.1700
Data Index: 4328631 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5376. Min Range: -9.5376
Max Act: 9.2251. Min Act: -0.1700
Data Index: 2498822 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5376. Min Range: -9.5376
Max Act: 9.1001. Min Act: -0.1700
Data Index: 4494890 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5376. Min Range: -9.5376
Max Act: 9.1001. Min Act: -0.1700
Data Index: 101379 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5376. Min Range: -9.5376
Max Act: 8.9751. Min Act: -0.1700
Data Index: 4573060 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5376. Min Range: -9.5376
Max Act: 8.9751. Min Act: -0.1700
Data Index: 6514003 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5376. Min Range: -9.5376
Max Act: 8.9751. Min Act: -0.1700
Data Index: 8463499 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5376. Min Range: -9.5376
Max Act: 8.9126. Min Act: -0.1700
Data Index: 2535893 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5376. Min Range: -9.5376
Max Act: 8.9126. Min Act: -0.1695
Data Index: 2367205 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5376. Min Range: -9.5376
Max Act: 8.8501. Min Act: -0.1700
Data Index: 1993763 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5376. Min Range: -9.5376
Max Act: 8.8501. Min Act: -0.1700
Data Index: 6512221 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5376. Min Range: -9.5376
Max Act: 8.7876. Min Act: -0.1700
Data Index: 3643252 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5376. Min Range: -9.5376
Max Act: 8.7876. Min Act: -0.1700
Data Index: 4600016 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5376. Min Range: -9.5376
Max Act: 8.7876. Min Act: -0.1700
Data Index: 4530325 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5376. Min Range: -9.5376
Max Act: 8.7876. Min Act: -0.1700
Data Index: 240484 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19