Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2816 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5113. Min Range: -8.5113
Max Act: 8.5113. Min Act: -0.1700
Data Index: 3900566 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5113. Min Range: -8.5113
Max Act: 8.3863. Min Act: -0.1700
Data Index: 5568345 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5113. Min Range: -8.5113
Max Act: 8.3238. Min Act: -0.1700
Data Index: 6339501 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5113. Min Range: -8.5113
Max Act: 8.3550. Min Act: -0.1700
Data Index: 8501169 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5113. Min Range: -8.5113
Max Act: 8.2613. Min Act: -0.1700
Data Index: 2022419 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5113. Min Range: -8.5113
Max Act: 8.1988. Min Act: -0.1700
Data Index: 4264942 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5113. Min Range: -8.5113
Max Act: 8.1050. Min Act: -0.1700
Data Index: 6365160 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5113. Min Range: -8.5113
Max Act: 8.0113. Min Act: -0.1700
Data Index: 5519295 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5113. Min Range: -8.5113
Max Act: 7.9800. Min Act: -0.1700
Data Index: 5421915 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5113. Min Range: -8.5113
Max Act: 7.9488. Min Act: -0.1700
Data Index: 7329170 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5113. Min Range: -8.5113
Max Act: 7.8863. Min Act: -0.1700
Data Index: 545116 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5113. Min Range: -8.5113
Max Act: 7.8550. Min Act: -0.1700
Data Index: 5095972 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5113. Min Range: -8.5113
Max Act: 7.8238. Min Act: -0.1700
Data Index: 4780454 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5113. Min Range: -8.5113
Max Act: 7.7925. Min Act: -0.1700
Data Index: 2903028 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5113. Min Range: -8.5113
Max Act: 7.7925. Min Act: -0.1700
Data Index: 3361196 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5113. Min Range: -8.5113
Max Act: 7.7613. Min Act: -0.1700
Data Index: 617625 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5113. Min Range: -8.5113
Max Act: 7.7925. Min Act: -0.1700
Data Index: 373925 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5113. Min Range: -8.5113
Max Act: 7.7300. Min Act: -0.1700
Data Index: 2551522 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5113. Min Range: -8.5113
Max Act: 7.7300. Min Act: -0.1700
Data Index: 8753025 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5113. Min Range: -8.5113
Max Act: 7.7300. Min Act: -0.1700
Data Index: 8430982 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19