Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2481 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2641. Min Range: -7.2641
Max Act: 7.2641. Min Act: -0.1700
Data Index: 7892379 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2641. Min Range: -7.2641
Max Act: 7.2328. Min Act: -0.1700
Data Index: 1799769 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2641. Min Range: -7.2641
Max Act: 7.2328. Min Act: -0.1700
Data Index: 2681275 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2641. Min Range: -7.2641
Max Act: 7.2016. Min Act: -0.1700
Data Index: 3166035 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2641. Min Range: -7.2641
Max Act: 7.2016. Min Act: -0.1700
Data Index: 1584011 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2641. Min Range: -7.2641
Max Act: 7.1391. Min Act: -0.1700
Data Index: 5817855 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2641. Min Range: -7.2641
Max Act: 7.1391. Min Act: -0.1700
Data Index: 8411703 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2641. Min Range: -7.2641
Max Act: 7.1391. Min Act: -0.1700
Data Index: 7752444 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2641. Min Range: -7.2641
Max Act: 7.0766. Min Act: -0.1700
Data Index: 8822207 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2641. Min Range: -7.2641
Max Act: 7.0453. Min Act: -0.1700
Data Index: 5577628 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2641. Min Range: -7.2641
Max Act: 7.0453. Min Act: -0.1700
Data Index: 5114651 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2641. Min Range: -7.2641
Max Act: 6.9828. Min Act: -0.1700
Data Index: 7663240 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2641. Min Range: -7.2641
Max Act: 6.9516. Min Act: -0.1700
Data Index: 5212123 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2641. Min Range: -7.2641
Max Act: 6.9516. Min Act: -0.1700
Data Index: 6074382 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2641. Min Range: -7.2641
Max Act: 6.9828. Min Act: -0.1700
Data Index: 3755576 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2641. Min Range: -7.2641
Max Act: 6.9203. Min Act: -0.1700
Data Index: 6219419 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2641. Min Range: -7.2641
Max Act: 6.9516. Min Act: -0.1700
Data Index: 4209997 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2641. Min Range: -7.2641
Max Act: 6.9203. Min Act: -0.1700
Data Index: 7070521 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2641. Min Range: -7.2641
Max Act: 6.9828. Min Act: -0.1700
Data Index: 2974161 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2641. Min Range: -7.2641
Max Act: 6.9203. Min Act: -0.1700
Data Index: 1172079 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #19