Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3670 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.9929. Min Act: -0.1700
Data Index: 2779854 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.9929. Min Act: -0.1700
Data Index: 3457141 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.8679. Min Act: -0.1700
Data Index: 4897469 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.8366. Min Act: -0.1700
Data Index: 8456483 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.8054. Min Act: -0.1700
Data Index: 793737 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.8054. Min Act: -0.1700
Data Index: 1549255 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.7741. Min Act: -0.1700
Data Index: 1449992 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.7741. Min Act: -0.1700
Data Index: 2030032 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.7429. Min Act: -0.1700
Data Index: 2257686 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.7429. Min Act: -0.1700
Data Index: 3497507 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.7429. Min Act: -0.1700
Data Index: 1412993 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.7429. Min Act: -0.1700
Data Index: 6334558 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.7741. Min Act: -0.1700
Data Index: 3628823 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.7116. Min Act: -0.1700
Data Index: 8447589 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.7116. Min Act: -0.1700
Data Index: 2932903 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.7116. Min Act: -0.1700
Data Index: 2803864 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.6804. Min Act: -0.1700
Data Index: 1156049 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.6179. Min Act: -0.1700
Data Index: 45063 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.6491. Min Act: -0.1700
Data Index: 1746220 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.6491. Min Act: -0.1700
Data Index: 1079494 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #19