Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 939 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8103. Min Range: -6.8103
Max Act: 6.8103. Min Act: -0.1700
Data Index: 2001209 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8103. Min Range: -6.8103
Max Act: 6.6853. Min Act: -0.1700
Data Index: 1270790 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8103. Min Range: -6.8103
Max Act: 6.6853. Min Act: -0.1700
Data Index: 984135 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8103. Min Range: -6.8103
Max Act: 6.6853. Min Act: -0.1700
Data Index: 278493 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8103. Min Range: -6.8103
Max Act: 6.6853. Min Act: -0.1700
Data Index: 8139149 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8103. Min Range: -6.8103
Max Act: 6.6853. Min Act: -0.1700
Data Index: 4423662 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8103. Min Range: -6.8103
Max Act: 6.7165. Min Act: -0.1700
Data Index: 8594669 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8103. Min Range: -6.8103
Max Act: 6.6540. Min Act: -0.1700
Data Index: 4119040 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8103. Min Range: -6.8103
Max Act: 6.6540. Min Act: -0.1700
Data Index: 7063424 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8103. Min Range: -6.8103
Max Act: 6.6228. Min Act: -0.1700
Data Index: 5366014 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8103. Min Range: -6.8103
Max Act: 6.6228. Min Act: -0.1700
Data Index: 429682 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8103. Min Range: -6.8103
Max Act: 6.6228. Min Act: -0.1700
Data Index: 7774059 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8103. Min Range: -6.8103
Max Act: 6.5915. Min Act: -0.1700
Data Index: 665601 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8103. Min Range: -6.8103
Max Act: 6.5915. Min Act: -0.1700
Data Index: 2112600 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8103. Min Range: -6.8103
Max Act: 6.6228. Min Act: -0.1700
Data Index: 5270777 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8103. Min Range: -6.8103
Max Act: 6.5603. Min Act: -0.1700
Data Index: 2870392 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8103. Min Range: -6.8103
Max Act: 6.5603. Min Act: -0.1700
Data Index: 236592 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8103. Min Range: -6.8103
Max Act: 6.5603. Min Act: -0.1700
Data Index: 6020793 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8103. Min Range: -6.8103
Max Act: 6.5603. Min Act: -0.1700
Data Index: 6596003 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8103. Min Range: -6.8103
Max Act: 6.5603. Min Act: -0.1700
Data Index: 2371260 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #19