Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5271 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5843. Min Range: -6.5843
Max Act: 6.5843. Min Act: -0.1700
Data Index: 4444041 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5843. Min Range: -6.5843
Max Act: 6.2718. Min Act: -0.1700
Data Index: 5430453 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5843. Min Range: -6.5843
Max Act: 6.2093. Min Act: -0.1700
Data Index: 7206085 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5843. Min Range: -6.5843
Max Act: 6.1781. Min Act: -0.1700
Data Index: 4930067 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5843. Min Range: -6.5843
Max Act: 6.0843. Min Act: -0.1700
Data Index: 5290555 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5843. Min Range: -6.5843
Max Act: 6.1468. Min Act: -0.1700
Data Index: 4029770 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5843. Min Range: -6.5843
Max Act: 6.0843. Min Act: -0.1700
Data Index: 4750176 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5843. Min Range: -6.5843
Max Act: 6.0843. Min Act: -0.1700
Data Index: 3840947 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5843. Min Range: -6.5843
Max Act: 6.0531. Min Act: -0.1700
Data Index: 2160461 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5843. Min Range: -6.5843
Max Act: 6.0531. Min Act: -0.1700
Data Index: 8012592 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5843. Min Range: -6.5843
Max Act: 6.0531. Min Act: -0.1700
Data Index: 5649700 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5843. Min Range: -6.5843
Max Act: 6.0531. Min Act: -0.1700
Data Index: 7487541 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5843. Min Range: -6.5843
Max Act: 6.0218. Min Act: -0.1700
Data Index: 7692231 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5843. Min Range: -6.5843
Max Act: 6.0218. Min Act: -0.1700
Data Index: 5668547 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5843. Min Range: -6.5843
Max Act: 5.9906. Min Act: -0.1700
Data Index: 921659 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5843. Min Range: -6.5843
Max Act: 5.9906. Min Act: -0.1700
Data Index: 13038 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5843. Min Range: -6.5843
Max Act: 6.0218. Min Act: -0.1700
Data Index: 5124143 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5843. Min Range: -6.5843
Max Act: 5.9906. Min Act: -0.1700
Data Index: 4847099 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5843. Min Range: -6.5843
Max Act: 5.9906. Min Act: -0.1700
Data Index: 344186 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5843. Min Range: -6.5843
Max Act: 5.9593. Min Act: -0.1700
Data Index: 462554 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19