Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3628 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6055. Min Range: -6.6055
Max Act: 6.6055. Min Act: -0.1700
Data Index: 3102159 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6055. Min Range: -6.6055
Max Act: 6.2618. Min Act: -0.1700
Data Index: 3368726 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6055. Min Range: -6.6055
Max Act: 6.2930. Min Act: -0.1700
Data Index: 380911 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6055. Min Range: -6.6055
Max Act: 6.1993. Min Act: -0.1700
Data Index: 3314906 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6055. Min Range: -6.6055
Max Act: 6.1055. Min Act: -0.1700
Data Index: 7125102 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6055. Min Range: -6.6055
Max Act: 6.0430. Min Act: -0.1700
Data Index: 6781963 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6055. Min Range: -6.6055
Max Act: 5.8868. Min Act: -0.1700
Data Index: 1620393 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6055. Min Range: -6.6055
Max Act: 5.8868. Min Act: -0.1700
Data Index: 5607002 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6055. Min Range: -6.6055
Max Act: 5.8868. Min Act: -0.1700
Data Index: 4441359 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6055. Min Range: -6.6055
Max Act: 5.8243. Min Act: -0.1700
Data Index: 6001564 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6055. Min Range: -6.6055
Max Act: 5.8243. Min Act: -0.1700
Data Index: 2556007 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6055. Min Range: -6.6055
Max Act: 5.8555. Min Act: -0.1700
Data Index: 7779657 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6055. Min Range: -6.6055
Max Act: 5.8243. Min Act: -0.1700
Data Index: 100960 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6055. Min Range: -6.6055
Max Act: 5.8555. Min Act: -0.1700
Data Index: 2156693 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6055. Min Range: -6.6055
Max Act: 5.7930. Min Act: -0.1700
Data Index: 4985905 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6055. Min Range: -6.6055
Max Act: 5.7930. Min Act: -0.1700
Data Index: 320977 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6055. Min Range: -6.6055
Max Act: 5.7930. Min Act: -0.1700
Data Index: 4114996 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6055. Min Range: -6.6055
Max Act: 5.7930. Min Act: -0.1700
Data Index: 1667068 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6055. Min Range: -6.6055
Max Act: 5.7618. Min Act: -0.1700
Data Index: 752718 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6055. Min Range: -6.6055
Max Act: 5.7618. Min Act: -0.1700
Data Index: 6198241 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #19