Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2054 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5014. Min Range: -8.5014
Max Act: 8.5014. Min Act: -0.1700
Data Index: 7681193 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5014. Min Range: -8.5014
Max Act: 8.1576. Min Act: -0.1700
Data Index: 6758610 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5014. Min Range: -8.5014
Max Act: 8.0951. Min Act: -0.1700
Data Index: 7533244 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5014. Min Range: -8.5014
Max Act: 7.8139. Min Act: -0.1700
Data Index: 1085909 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5014. Min Range: -8.5014
Max Act: 7.7514. Min Act: -0.1700
Data Index: 8827459 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5014. Min Range: -8.5014
Max Act: 7.7826. Min Act: -0.1700
Data Index: 3544559 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5014. Min Range: -8.5014
Max Act: 7.7826. Min Act: -0.1700
Data Index: 3307787 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5014. Min Range: -8.5014
Max Act: 7.7514. Min Act: -0.1700
Data Index: 32441 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5014. Min Range: -8.5014
Max Act: 7.7201. Min Act: -0.1700
Data Index: 2067723 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5014. Min Range: -8.5014
Max Act: 7.7201. Min Act: -0.1700
Data Index: 865457 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5014. Min Range: -8.5014
Max Act: 7.7201. Min Act: -0.1700
Data Index: 2721405 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5014. Min Range: -8.5014
Max Act: 7.6889. Min Act: -0.1700
Data Index: 3593045 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5014. Min Range: -8.5014
Max Act: 7.6264. Min Act: -0.1700
Data Index: 7764689 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5014. Min Range: -8.5014
Max Act: 7.6264. Min Act: -0.1700
Data Index: 981371 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5014. Min Range: -8.5014
Max Act: 7.6264. Min Act: -0.1700
Data Index: 1784746 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5014. Min Range: -8.5014
Max Act: 7.5639. Min Act: -0.1700
Data Index: 8301888 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5014. Min Range: -8.5014
Max Act: 7.5639. Min Act: -0.1700
Data Index: 2407961 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5014. Min Range: -8.5014
Max Act: 7.5639. Min Act: -0.1700
Data Index: 484015 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5014. Min Range: -8.5014
Max Act: 7.5951. Min Act: -0.1700
Data Index: 6166137 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5014. Min Range: -8.5014
Max Act: 7.5951. Min Act: -0.1700
Data Index: 7742188 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19