Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2649 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1781. Min Range: -10.1781
Max Act: 10.1781. Min Act: -0.1700
Data Index: 5994124 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1781. Min Range: -10.1781
Max Act: 9.8031. Min Act: -0.1700
Data Index: 3249535 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1781. Min Range: -10.1781
Max Act: 9.8031. Min Act: -0.1700
Data Index: 2150978 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1781. Min Range: -10.1781
Max Act: 9.7406. Min Act: -0.1700
Data Index: 6655895 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1781. Min Range: -10.1781
Max Act: 9.6781. Min Act: -0.1700
Data Index: 1199816 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1781. Min Range: -10.1781
Max Act: 9.6781. Min Act: -0.1700
Data Index: 5411700 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1781. Min Range: -10.1781
Max Act: 9.6781. Min Act: -0.1700
Data Index: 8102269 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1781. Min Range: -10.1781
Max Act: 9.6781. Min Act: -0.1700
Data Index: 3437576 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1781. Min Range: -10.1781
Max Act: 9.6781. Min Act: -0.1700
Data Index: 5701421 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1781. Min Range: -10.1781
Max Act: 9.6156. Min Act: -0.1700
Data Index: 3723815 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1781. Min Range: -10.1781
Max Act: 9.6156. Min Act: -0.1700
Data Index: 5800943 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1781. Min Range: -10.1781
Max Act: 9.6156. Min Act: -0.1700
Data Index: 4512462 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1781. Min Range: -10.1781
Max Act: 9.6156. Min Act: -0.1700
Data Index: 5674333 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1781. Min Range: -10.1781
Max Act: 9.5531. Min Act: -0.1700
Data Index: 3038969 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1781. Min Range: -10.1781
Max Act: 9.5531. Min Act: -0.1700
Data Index: 300787 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1781. Min Range: -10.1781
Max Act: 9.4906. Min Act: -0.1700
Data Index: 3638175 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1781. Min Range: -10.1781
Max Act: 9.4906. Min Act: -0.1700
Data Index: 3572782 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1781. Min Range: -10.1781
Max Act: 9.4906. Min Act: -0.1700
Data Index: 8214274 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1781. Min Range: -10.1781
Max Act: 9.4906. Min Act: -0.1700
Data Index: 2218730 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1781. Min Range: -10.1781
Max Act: 9.3656. Min Act: -0.1700
Data Index: 2186742 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #19