Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2919 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8058. Min Range: -5.8058
Max Act: 5.8058. Min Act: -0.1700
Data Index: 31632 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8058. Min Range: -5.8058
Max Act: 5.7746. Min Act: -0.1700
Data Index: 5899073 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8058. Min Range: -5.8058
Max Act: 5.7746. Min Act: -0.1700
Data Index: 1157041 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8058. Min Range: -5.8058
Max Act: 5.7433. Min Act: -0.1700
Data Index: 2021109 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8058. Min Range: -5.8058
Max Act: 5.7433. Min Act: -0.1700
Data Index: 5261138 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8058. Min Range: -5.8058
Max Act: 5.7433. Min Act: -0.1700
Data Index: 4537603 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8058. Min Range: -5.8058
Max Act: 5.7121. Min Act: -0.1700
Data Index: 6993998 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8058. Min Range: -5.8058
Max Act: 5.7121. Min Act: -0.1700
Data Index: 720512 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8058. Min Range: -5.8058
Max Act: 5.7121. Min Act: -0.1700
Data Index: 554983 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8058. Min Range: -5.8058
Max Act: 5.6808. Min Act: -0.1700
Data Index: 586603 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8058. Min Range: -5.8058
Max Act: 5.6496. Min Act: -0.1700
Data Index: 4808005 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8058. Min Range: -5.8058
Max Act: 5.7121. Min Act: -0.1700
Data Index: 5017754 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8058. Min Range: -5.8058
Max Act: 5.6808. Min Act: -0.1700
Data Index: 2653923 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8058. Min Range: -5.8058
Max Act: 5.6496. Min Act: -0.1700
Data Index: 1795294 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8058. Min Range: -5.8058
Max Act: 5.6496. Min Act: -0.1700
Data Index: 4182710 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8058. Min Range: -5.8058
Max Act: 5.6808. Min Act: -0.1700
Data Index: 1069968 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8058. Min Range: -5.8058
Max Act: 5.6496. Min Act: -0.1700
Data Index: 7872846 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8058. Min Range: -5.8058
Max Act: 5.6496. Min Act: -0.1700
Data Index: 6336411 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8058. Min Range: -5.8058
Max Act: 5.6496. Min Act: -0.1700
Data Index: 8401666 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8058. Min Range: -5.8058
Max Act: 5.6496. Min Act: -0.1700
Data Index: 246546 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #19