Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6374 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8907. Min Range: -6.8907
Max Act: 6.8907. Min Act: -0.1700
Data Index: 8616694 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8907. Min Range: -6.8907
Max Act: 6.8594. Min Act: -0.1700
Data Index: 7122263 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8907. Min Range: -6.8907
Max Act: 6.5782. Min Act: -0.1700
Data Index: 10037 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8907. Min Range: -6.8907
Max Act: 6.4844. Min Act: -0.1700
Data Index: 5095897 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8907. Min Range: -6.8907
Max Act: 6.4219. Min Act: -0.1700
Data Index: 7778366 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8907. Min Range: -6.8907
Max Act: 6.3907. Min Act: -0.1700
Data Index: 2644013 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8907. Min Range: -6.8907
Max Act: 6.3594. Min Act: -0.1700
Data Index: 6364865 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8907. Min Range: -6.8907
Max Act: 6.3594. Min Act: -0.1700
Data Index: 6080163 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8907. Min Range: -6.8907
Max Act: 6.2969. Min Act: -0.1700
Data Index: 8816258 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8907. Min Range: -6.8907
Max Act: 6.3282. Min Act: -0.1700
Data Index: 6035925 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8907. Min Range: -6.8907
Max Act: 6.3282. Min Act: -0.1700
Data Index: 8261400 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8907. Min Range: -6.8907
Max Act: 6.3282. Min Act: -0.1700
Data Index: 10038 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8907. Min Range: -6.8907
Max Act: 6.2969. Min Act: -0.1700
Data Index: 3570498 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8907. Min Range: -6.8907
Max Act: 6.2657. Min Act: -0.1700
Data Index: 2644014 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8907. Min Range: -6.8907
Max Act: 6.2657. Min Act: -0.1700
Data Index: 6475960 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8907. Min Range: -6.8907
Max Act: 6.2969. Min Act: -0.1700
Data Index: 647858 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8907. Min Range: -6.8907
Max Act: 6.2657. Min Act: -0.1700
Data Index: 5549700 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8907. Min Range: -6.8907
Max Act: 6.2657. Min Act: -0.1700
Data Index: 178747 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8907. Min Range: -6.8907
Max Act: 6.2344. Min Act: -0.1700
Data Index: 1493601 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8907. Min Range: -6.8907
Max Act: 6.2344. Min Act: -0.1700
Data Index: 1619006 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19