Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2432 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7733. Min Range: -8.7733
Max Act: 8.7733. Min Act: -0.1700
Data Index: 7511022 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7733. Min Range: -8.7733
Max Act: 8.4608. Min Act: -0.1700
Data Index: 3863706 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7733. Min Range: -8.7733
Max Act: 8.4608. Min Act: -0.1700
Data Index: 1102804 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7733. Min Range: -8.7733
Max Act: 8.3983. Min Act: -0.1700
Data Index: 2689966 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7733. Min Range: -8.7733
Max Act: 8.3983. Min Act: -0.1700
Data Index: 195445 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7733. Min Range: -8.7733
Max Act: 8.2733. Min Act: -0.1700
Data Index: 7398234 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7733. Min Range: -8.7733
Max Act: 8.2108. Min Act: -0.1700
Data Index: 1577372 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7733. Min Range: -8.7733
Max Act: 8.1796. Min Act: -0.1700
Data Index: 4098186 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7733. Min Range: -8.7733
Max Act: 8.1796. Min Act: -0.1700
Data Index: 8449393 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7733. Min Range: -8.7733
Max Act: 8.1796. Min Act: -0.1700
Data Index: 3044817 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7733. Min Range: -8.7733
Max Act: 8.0858. Min Act: -0.1700
Data Index: 7887391 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7733. Min Range: -8.7733
Max Act: 7.9921. Min Act: -0.1699
Data Index: 8708231 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7733. Min Range: -8.7733
Max Act: 7.9921. Min Act: -0.1700
Data Index: 4668167 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7733. Min Range: -8.7733
Max Act: 7.9921. Min Act: -0.1700
Data Index: 718027 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7733. Min Range: -8.7733
Max Act: 7.9608. Min Act: -0.1700
Data Index: 1934621 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7733. Min Range: -8.7733
Max Act: 7.9296. Min Act: -0.1700
Data Index: 966722 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7733. Min Range: -8.7733
Max Act: 7.9296. Min Act: -0.1700
Data Index: 5008046 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7733. Min Range: -8.7733
Max Act: 7.9608. Min Act: -0.1700
Data Index: 371082 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7733. Min Range: -8.7733
Max Act: 7.8983. Min Act: -0.1700
Data Index: 3847875 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7733. Min Range: -8.7733
Max Act: 7.8983. Min Act: -0.1700
Data Index: 4668160 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #19