Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1946 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0617. Min Range: -6.0617
Max Act: 6.0617. Min Act: -0.1700
Data Index: 6315525 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0617. Min Range: -6.0617
Max Act: 5.9055. Min Act: -0.1700
Data Index: 8266970 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0617. Min Range: -6.0617
Max Act: 5.7805. Min Act: -0.1700
Data Index: 4744158 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0617. Min Range: -6.0617
Max Act: 5.7805. Min Act: -0.1700
Data Index: 5868803 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0617. Min Range: -6.0617
Max Act: 5.7805. Min Act: -0.1700
Data Index: 8032502 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0617. Min Range: -6.0617
Max Act: 5.7805. Min Act: -0.1700
Data Index: 5560065 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0617. Min Range: -6.0617
Max Act: 5.7805. Min Act: -0.1700
Data Index: 1007982 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0617. Min Range: -6.0617
Max Act: 5.7492. Min Act: -0.1700
Data Index: 4904205 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0617. Min Range: -6.0617
Max Act: 5.7492. Min Act: -0.1700
Data Index: 6638670 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0617. Min Range: -6.0617
Max Act: 5.7492. Min Act: -0.1700
Data Index: 4089011 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0617. Min Range: -6.0617
Max Act: 5.6867. Min Act: -0.1700
Data Index: 5537195 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0617. Min Range: -6.0617
Max Act: 5.7180. Min Act: -0.1700
Data Index: 3685523 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0617. Min Range: -6.0617
Max Act: 5.6867. Min Act: -0.1700
Data Index: 6429346 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0617. Min Range: -6.0617
Max Act: 5.6867. Min Act: -0.1700
Data Index: 7336934 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0617. Min Range: -6.0617
Max Act: 5.6867. Min Act: -0.1700
Data Index: 2688676 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0617. Min Range: -6.0617
Max Act: 5.6555. Min Act: -0.1700
Data Index: 5688329 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0617. Min Range: -6.0617
Max Act: 5.6555. Min Act: -0.1700
Data Index: 941229 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0617. Min Range: -6.0617
Max Act: 5.6242. Min Act: -0.1700
Data Index: 6294589 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0617. Min Range: -6.0617
Max Act: 5.6555. Min Act: -0.1700
Data Index: 5953416 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0617. Min Range: -6.0617
Max Act: 5.6867. Min Act: -0.1700
Data Index: 4985370 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #19