Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3258 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9853. Min Range: -4.9853
Max Act: 4.9853. Min Act: -0.1700
Data Index: 7570931 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9853. Min Range: -4.9853
Max Act: 4.9853. Min Act: -0.1700
Data Index: 7747696 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9853. Min Range: -4.9853
Max Act: 4.9228. Min Act: -0.1700
Data Index: 3734827 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9853. Min Range: -4.9853
Max Act: 4.9228. Min Act: -0.1700
Data Index: 7747695 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9853. Min Range: -4.9853
Max Act: 4.9228. Min Act: -0.1700
Data Index: 496511 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9853. Min Range: -4.9853
Max Act: 4.9228. Min Act: -0.1700
Data Index: 1841539 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9853. Min Range: -4.9853
Max Act: 4.8915. Min Act: -0.1700
Data Index: 3298237 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9853. Min Range: -4.9853
Max Act: 4.8603. Min Act: -0.1700
Data Index: 7722768 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9853. Min Range: -4.9853
Max Act: 4.8603. Min Act: -0.1700
Data Index: 1820042 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9853. Min Range: -4.9853
Max Act: 4.8290. Min Act: -0.1700
Data Index: 4162183 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9853. Min Range: -4.9853
Max Act: 4.8290. Min Act: -0.1700
Data Index: 6923067 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9853. Min Range: -4.9853
Max Act: 4.8290. Min Act: -0.1700
Data Index: 3312836 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9853. Min Range: -4.9853
Max Act: 4.8290. Min Act: -0.1700
Data Index: 4034580 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9853. Min Range: -4.9853
Max Act: 4.8290. Min Act: -0.1700
Data Index: 1591896 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9853. Min Range: -4.9853
Max Act: 4.7978. Min Act: -0.1700
Data Index: 473474 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9853. Min Range: -4.9853
Max Act: 4.7978. Min Act: -0.1700
Data Index: 6288408 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9853. Min Range: -4.9853
Max Act: 4.7665. Min Act: -0.1700
Data Index: 1575764 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9853. Min Range: -4.9853
Max Act: 4.7665. Min Act: -0.1700
Data Index: 3210027 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9853. Min Range: -4.9853
Max Act: 4.7665. Min Act: -0.1700
Data Index: 1788801 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9853. Min Range: -4.9853
Max Act: 4.7665. Min Act: -0.1700
Data Index: 1457395 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19