Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6323 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9106. Min Range: -4.9106
Max Act: 4.9106. Min Act: -0.1700
Data Index: 3891349 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9106. Min Range: -4.9106
Max Act: 4.8794. Min Act: -0.1700
Data Index: 1175361 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9106. Min Range: -4.9106
Max Act: 4.8169. Min Act: -0.1700
Data Index: 3086275 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9106. Min Range: -4.9106
Max Act: 4.7856. Min Act: -0.1700
Data Index: 6358392 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9106. Min Range: -4.9106
Max Act: 4.7856. Min Act: -0.1700
Data Index: 6446695 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9106. Min Range: -4.9106
Max Act: 4.7544. Min Act: -0.1700
Data Index: 5171181 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9106. Min Range: -4.9106
Max Act: 4.7231. Min Act: -0.1700
Data Index: 8537726 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9106. Min Range: -4.9106
Max Act: 4.7231. Min Act: -0.1700
Data Index: 3776498 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9106. Min Range: -4.9106
Max Act: 4.6919. Min Act: -0.1700
Data Index: 2899333 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9106. Min Range: -4.9106
Max Act: 4.7231. Min Act: -0.1700
Data Index: 352075 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9106. Min Range: -4.9106
Max Act: 4.6919. Min Act: -0.1700
Data Index: 7414399 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9106. Min Range: -4.9106
Max Act: 4.6919. Min Act: -0.1700
Data Index: 4545395 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9106. Min Range: -4.9106
Max Act: 4.6919. Min Act: -0.1700
Data Index: 7736593 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9106. Min Range: -4.9106
Max Act: 4.6919. Min Act: -0.1700
Data Index: 4815569 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9106. Min Range: -4.9106
Max Act: 4.6919. Min Act: -0.1700
Data Index: 5500555 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9106. Min Range: -4.9106
Max Act: 4.6606. Min Act: -0.1700
Data Index: 3907638 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9106. Min Range: -4.9106
Max Act: 4.6606. Min Act: -0.1700
Data Index: 7672889 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9106. Min Range: -4.9106
Max Act: 4.6919. Min Act: -0.1700
Data Index: 3675890 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9106. Min Range: -4.9106
Max Act: 4.6919. Min Act: -0.1700
Data Index: 2391804 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9106. Min Range: -4.9106
Max Act: 4.6919. Min Act: -0.1700
Data Index: 2852798 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #19