Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3063 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.9989. Min Act: -0.1700
Data Index: 6831384 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.9677. Min Act: -0.1700
Data Index: 4088226 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.9677. Min Act: -0.1700
Data Index: 5438337 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.8739. Min Act: -0.1700
Data Index: 8121471 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.8426. Min Act: -0.1700
Data Index: 109749 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.8426. Min Act: -0.1700
Data Index: 1147930 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.8426. Min Act: -0.1700
Data Index: 1547974 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.8426. Min Act: -0.1700
Data Index: 4017322 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.8113. Min Act: -0.1700
Data Index: 4900063 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.8113. Min Act: -0.1700
Data Index: 3637810 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.7800. Min Act: -0.1700
Data Index: 6354608 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.7800. Min Act: -0.1700
Data Index: 7367145 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.7488. Min Act: -0.1700
Data Index: 820833 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.7800. Min Act: -0.1700
Data Index: 4759052 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.7800. Min Act: -0.1700
Data Index: 5964772 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.7800. Min Act: -0.1700
Data Index: 3434585 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.7800. Min Act: -0.1700
Data Index: 8657804 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.7800. Min Act: -0.1700
Data Index: 8804554 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.7800. Min Act: -0.1700
Data Index: 6943255 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.7175. Min Act: -0.1700
Data Index: 6720934 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19