Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5367 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 16.6974. Min Range: -16.6974
Max Act: 16.6974. Min Act: -0.1700
Data Index: 4569819 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.6974. Min Range: -16.6974
Max Act: 16.5724. Min Act: -0.1700
Data Index: 3110291 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.6974. Min Range: -16.6974
Max Act: 16.4474. Min Act: -0.1700
Data Index: 4569817 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.6974. Min Range: -16.6974
Max Act: 16.4474. Min Act: -0.1700
Data Index: 5003606 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.6974. Min Range: -16.6974
Max Act: 16.4474. Min Act: -0.1700
Data Index: 4569816 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.6974. Min Range: -16.6974
Max Act: 16.3224. Min Act: -0.1700
Data Index: 3110292 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.6974. Min Range: -16.6974
Max Act: 16.3224. Min Act: -0.1700
Data Index: 4569818 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.6974. Min Range: -16.6974
Max Act: 16.1974. Min Act: -0.1700
Data Index: 8569918 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.6974. Min Range: -16.6974
Max Act: 15.9474. Min Act: -0.1700
Data Index: 5354775 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.6974. Min Range: -16.6974
Max Act: 16.0724. Min Act: -0.1700
Data Index: 5354774 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.6974. Min Range: -16.6974
Max Act: 15.9474. Min Act: -0.1700
Data Index: 7830677 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.6974. Min Range: -16.6974
Max Act: 15.8224. Min Act: -0.1700
Data Index: 8569917 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.6974. Min Range: -16.6974
Max Act: 15.9474. Min Act: -0.1700
Data Index: 7487415 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.6974. Min Range: -16.6974
Max Act: 15.9474. Min Act: -0.1700
Data Index: 7062457 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.6974. Min Range: -16.6974
Max Act: 15.9474. Min Act: -0.1700
Data Index: 8182808 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.6974. Min Range: -16.6974
Max Act: 15.6974. Min Act: -0.1700
Data Index: 7830679 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.6974. Min Range: -16.6974
Max Act: 15.8224. Min Act: -0.1700
Data Index: 8796001 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.6974. Min Range: -16.6974
Max Act: 15.8224. Min Act: -0.1700
Data Index: 8569919 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.6974. Min Range: -16.6974
Max Act: 15.8224. Min Act: -0.1700
Data Index: 8182803 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.6974. Min Range: -16.6974
Max Act: 15.8224. Min Act: -0.1700
Data Index: 4165398 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #19