Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3503 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0092. Min Range: -5.0092
Max Act: 5.0092. Min Act: -0.1700
Data Index: 4671207 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.7592. Min Act: -0.1700
Data Index: 6920867 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.7592. Min Act: -0.1700
Data Index: 3291915 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.7592. Min Act: -0.1700
Data Index: 5359675 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.7592. Min Act: -0.1700
Data Index: 1623468 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.6967. Min Act: -0.1700
Data Index: 3961923 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.6967. Min Act: -0.1700
Data Index: 1099430 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.6654. Min Act: -0.1700
Data Index: 4288440 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.6342. Min Act: -0.1700
Data Index: 6883041 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.6029. Min Act: -0.1700
Data Index: 6531454 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.6342. Min Act: -0.1700
Data Index: 7196848 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.6029. Min Act: -0.1700
Data Index: 1961561 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.6029. Min Act: -0.1700
Data Index: 3829472 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.5717. Min Act: -0.1700
Data Index: 4472915 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.5717. Min Act: -0.1700
Data Index: 3171942 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.5717. Min Act: -0.1700
Data Index: 3441660 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.5717. Min Act: -0.1700
Data Index: 3664845 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.5717. Min Act: -0.1700
Data Index: 887628 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.5404. Min Act: -0.1700
Data Index: 5377631 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.5404. Min Act: -0.1700
Data Index: 3998729 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19