Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4591 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9913. Min Range: -2.9913
Max Act: 2.9913. Min Act: -0.1700
Data Index: 6181640 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9913. Min Range: -2.9913
Max Act: 2.9913. Min Act: -0.1700
Data Index: 2274245 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9913. Min Range: -2.9913
Max Act: 2.9438. Min Act: -0.1700
Data Index: 5411543 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9913. Min Range: -2.9913
Max Act: 2.8963. Min Act: -0.1700
Data Index: 6438484 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9913. Min Range: -2.9913
Max Act: 2.9122. Min Act: -0.1700
Data Index: 635282 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9913. Min Range: -2.9913
Max Act: 2.9122. Min Act: -0.1700
Data Index: 4590428 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9913. Min Range: -2.9913
Max Act: 2.8804. Min Act: -0.1700
Data Index: 7470151 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9913. Min Range: -2.9913
Max Act: 2.8646. Min Act: -0.1700
Data Index: 2247759 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9913. Min Range: -2.9913
Max Act: 2.8487. Min Act: -0.1700
Data Index: 8668994 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9913. Min Range: -2.9913
Max Act: 2.8487. Min Act: -0.1700
Data Index: 2548901 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9913. Min Range: -2.9913
Max Act: 2.8487. Min Act: -0.1700
Data Index: 6445936 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9913. Min Range: -2.9913
Max Act: 2.8328. Min Act: -0.1700
Data Index: 7141491 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9913. Min Range: -2.9913
Max Act: 2.8169. Min Act: -0.1700
Data Index: 8458519 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9913. Min Range: -2.9913
Max Act: 2.8169. Min Act: -0.1700
Data Index: 1152808 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9913. Min Range: -2.9913
Max Act: 2.8010. Min Act: -0.1700
Data Index: 3740464 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9913. Min Range: -2.9913
Max Act: 2.8169. Min Act: -0.1700
Data Index: 5036364 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9913. Min Range: -2.9913
Max Act: 2.8010. Min Act: -0.1700
Data Index: 2007922 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9913. Min Range: -2.9913
Max Act: 2.7850. Min Act: -0.1700
Data Index: 3816699 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9913. Min Range: -2.9913
Max Act: 2.8010. Min Act: -0.1700
Data Index: 7156118 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9913. Min Range: -2.9913
Max Act: 2.7850. Min Act: -0.1700
Data Index: 6659981 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19