Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1895 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3189. Min Range: -6.3189
Max Act: 6.3189. Min Act: -0.1700
Data Index: 3413893 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3189. Min Range: -6.3189
Max Act: 6.1002. Min Act: -0.1700
Data Index: 2763984 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3189. Min Range: -6.3189
Max Act: 6.1002. Min Act: -0.1700
Data Index: 6378112 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3189. Min Range: -6.3189
Max Act: 6.0064. Min Act: -0.1700
Data Index: 7228954 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3189. Min Range: -6.3189
Max Act: 5.9127. Min Act: -0.1700
Data Index: 6183458 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3189. Min Range: -6.3189
Max Act: 5.9127. Min Act: -0.1700
Data Index: 1641548 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3189. Min Range: -6.3189
Max Act: 5.9127. Min Act: -0.1700
Data Index: 6664987 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3189. Min Range: -6.3189
Max Act: 5.9127. Min Act: -0.1700
Data Index: 346585 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3189. Min Range: -6.3189
Max Act: 5.8814. Min Act: -0.1700
Data Index: 6632950 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3189. Min Range: -6.3189
Max Act: 5.8814. Min Act: -0.1700
Data Index: 6672575 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3189. Min Range: -6.3189
Max Act: 5.8502. Min Act: -0.1700
Data Index: 6745872 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3189. Min Range: -6.3189
Max Act: 5.8502. Min Act: -0.1700
Data Index: 6091256 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3189. Min Range: -6.3189
Max Act: 5.8189. Min Act: -0.1700
Data Index: 8012973 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3189. Min Range: -6.3189
Max Act: 5.8502. Min Act: -0.1700
Data Index: 5258479 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3189. Min Range: -6.3189
Max Act: 5.8189. Min Act: -0.1700
Data Index: 582276 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3189. Min Range: -6.3189
Max Act: 5.8189. Min Act: -0.1700
Data Index: 7089948 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3189. Min Range: -6.3189
Max Act: 5.8189. Min Act: -0.1700
Data Index: 4177173 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3189. Min Range: -6.3189
Max Act: 5.7877. Min Act: -0.1700
Data Index: 53280 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3189. Min Range: -6.3189
Max Act: 5.7877. Min Act: -0.1700
Data Index: 174156 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3189. Min Range: -6.3189
Max Act: 5.7564. Min Act: -0.1700
Data Index: 3034558 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19