Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3973 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4079. Min Range: -3.4079
Max Act: 3.4079. Min Act: -0.1700
Data Index: 8053676 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4079. Min Range: -3.4079
Max Act: 3.2981. Min Act: -0.1700
Data Index: 827227 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4079. Min Range: -3.4079
Max Act: 3.2824. Min Act: -0.1700
Data Index: 97795 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4079. Min Range: -3.4079
Max Act: 3.2510. Min Act: -0.1700
Data Index: 8529939 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4079. Min Range: -3.4079
Max Act: 3.2196. Min Act: -0.1700
Data Index: 8723224 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4079. Min Range: -3.4079
Max Act: 3.2039. Min Act: -0.1700
Data Index: 5834770 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4079. Min Range: -3.4079
Max Act: 3.1724. Min Act: -0.1700
Data Index: 6950434 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4079. Min Range: -3.4079
Max Act: 3.1409. Min Act: -0.1700
Data Index: 7568 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4079. Min Range: -3.4079
Max Act: 3.1567. Min Act: -0.1700
Data Index: 3432783 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4079. Min Range: -3.4079
Max Act: 3.1724. Min Act: -0.1700
Data Index: 456374 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4079. Min Range: -3.4079
Max Act: 3.1409. Min Act: -0.1700
Data Index: 567467 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4079. Min Range: -3.4079
Max Act: 3.1409. Min Act: -0.1700
Data Index: 6969007 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4079. Min Range: -3.4079
Max Act: 3.1409. Min Act: -0.1700
Data Index: 8386124 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4079. Min Range: -3.4079
Max Act: 3.1409. Min Act: -0.1700
Data Index: 3369487 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4079. Min Range: -3.4079
Max Act: 3.1252. Min Act: -0.1700
Data Index: 294251 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4079. Min Range: -3.4079
Max Act: 3.0779. Min Act: -0.1700
Data Index: 2796093 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4079. Min Range: -3.4079
Max Act: 3.0779. Min Act: -0.1700
Data Index: 4854243 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4079. Min Range: -3.4079
Max Act: 3.0937. Min Act: -0.1700
Data Index: 3338866 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4079. Min Range: -3.4079
Max Act: 3.0937. Min Act: -0.1700
Data Index: 7832612 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4079. Min Range: -3.4079
Max Act: 3.0779. Min Act: -0.1700
Data Index: 3585710 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #19