Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5004 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1896. Min Range: -6.1896
Max Act: 6.1896. Min Act: -0.1700
Data Index: 3211561 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1896. Min Range: -6.1896
Max Act: 5.9708. Min Act: -0.1700
Data Index: 6952709 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1896. Min Range: -6.1896
Max Act: 5.8458. Min Act: -0.1700
Data Index: 1098001 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1896. Min Range: -6.1896
Max Act: 5.7833. Min Act: -0.1700
Data Index: 131275 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1896. Min Range: -6.1896
Max Act: 5.7208. Min Act: -0.1700
Data Index: 3912849 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1896. Min Range: -6.1896
Max Act: 5.6896. Min Act: -0.1700
Data Index: 299144 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1896. Min Range: -6.1896
Max Act: 5.6271. Min Act: -0.1700
Data Index: 6538334 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1896. Min Range: -6.1896
Max Act: 5.5958. Min Act: -0.1700
Data Index: 3395243 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1896. Min Range: -6.1896
Max Act: 5.5958. Min Act: -0.1700
Data Index: 3912847 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1896. Min Range: -6.1896
Max Act: 5.5021. Min Act: -0.1700
Data Index: 4177893 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1896. Min Range: -6.1896
Max Act: 5.5333. Min Act: -0.1700
Data Index: 8046370 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1896. Min Range: -6.1896
Max Act: 5.5333. Min Act: -0.1700
Data Index: 294484 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1896. Min Range: -6.1896
Max Act: 5.5021. Min Act: -0.1700
Data Index: 1872711 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1896. Min Range: -6.1896
Max Act: 5.4396. Min Act: -0.1700
Data Index: 5339559 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1896. Min Range: -6.1896
Max Act: 5.4708. Min Act: -0.1700
Data Index: 5506957 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1896. Min Range: -6.1896
Max Act: 5.4708. Min Act: -0.1700
Data Index: 797320 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1896. Min Range: -6.1896
Max Act: 5.4708. Min Act: -0.1700
Data Index: 1807048 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1896. Min Range: -6.1896
Max Act: 5.4708. Min Act: -0.1700
Data Index: 3084607 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1896. Min Range: -6.1896
Max Act: 5.4396. Min Act: -0.1700
Data Index: 5274473 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1896. Min Range: -6.1896
Max Act: 5.4396. Min Act: -0.1700
Data Index: 4591872 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19