Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1644 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1717. Min Range: -8.1717
Max Act: 8.1717. Min Act: -0.1700
Data Index: 5841130 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1717. Min Range: -8.1717
Max Act: 7.9217. Min Act: -0.1700
Data Index: 3452483 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1717. Min Range: -8.1717
Max Act: 7.8592. Min Act: -0.1700
Data Index: 6392113 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1717. Min Range: -8.1717
Max Act: 7.7967. Min Act: -0.1700
Data Index: 3671349 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1717. Min Range: -8.1717
Max Act: 7.7342. Min Act: -0.1700
Data Index: 7200494 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1717. Min Range: -8.1717
Max Act: 7.7342. Min Act: -0.1700
Data Index: 2936781 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1717. Min Range: -8.1717
Max Act: 7.7342. Min Act: -0.1700
Data Index: 1348652 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1717. Min Range: -8.1717
Max Act: 7.7342. Min Act: -0.1700
Data Index: 6554653 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1717. Min Range: -8.1717
Max Act: 7.6717. Min Act: -0.1700
Data Index: 6673396 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1717. Min Range: -8.1717
Max Act: 7.6092. Min Act: -0.1700
Data Index: 2070626 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1717. Min Range: -8.1717
Max Act: 7.5467. Min Act: -0.1700
Data Index: 2935848 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1717. Min Range: -8.1717
Max Act: 7.5467. Min Act: -0.1700
Data Index: 1353292 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1717. Min Range: -8.1717
Max Act: 7.6092. Min Act: -0.1700
Data Index: 4370297 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1717. Min Range: -8.1717
Max Act: 7.5467. Min Act: -0.1700
Data Index: 1403837 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1717. Min Range: -8.1717
Max Act: 7.5154. Min Act: -0.1700
Data Index: 7479148 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1717. Min Range: -8.1717
Max Act: 7.5154. Min Act: -0.1700
Data Index: 4749457 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1717. Min Range: -8.1717
Max Act: 7.4842. Min Act: -0.1700
Data Index: 877022 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1717. Min Range: -8.1717
Max Act: 7.4529. Min Act: -0.1700
Data Index: 2595054 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1717. Min Range: -8.1717
Max Act: 7.4529. Min Act: -0.1700
Data Index: 3267492 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1717. Min Range: -8.1717
Max Act: 7.4529. Min Act: -0.1700
Data Index: 5108818 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19