Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2843 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4102. Min Range: -6.4102
Max Act: 6.4102. Min Act: -0.1700
Data Index: 4749555 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4102. Min Range: -6.4102
Max Act: 6.3477. Min Act: -0.1700
Data Index: 2946180 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4102. Min Range: -6.4102
Max Act: 6.1915. Min Act: -0.1700
Data Index: 782055 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4102. Min Range: -6.4102
Max Act: 6.0977. Min Act: -0.1700
Data Index: 1878804 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4102. Min Range: -6.4102
Max Act: 6.0040. Min Act: -0.1700
Data Index: 7392241 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4102. Min Range: -6.4102
Max Act: 5.9415. Min Act: -0.1700
Data Index: 2346926 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4102. Min Range: -6.4102
Max Act: 5.9102. Min Act: -0.1700
Data Index: 5872743 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4102. Min Range: -6.4102
Max Act: 5.9102. Min Act: -0.1700
Data Index: 4212837 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4102. Min Range: -6.4102
Max Act: 5.9102. Min Act: -0.1700
Data Index: 76640 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4102. Min Range: -6.4102
Max Act: 5.9102. Min Act: -0.1700
Data Index: 709517 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4102. Min Range: -6.4102
Max Act: 5.9102. Min Act: -0.1700
Data Index: 1015286 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4102. Min Range: -6.4102
Max Act: 5.8165. Min Act: -0.1700
Data Index: 4298177 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4102. Min Range: -6.4102
Max Act: 5.7852. Min Act: -0.1700
Data Index: 7958977 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4102. Min Range: -6.4102
Max Act: 5.7852. Min Act: -0.1700
Data Index: 4759631 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4102. Min Range: -6.4102
Max Act: 5.7540. Min Act: -0.1700
Data Index: 5626029 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4102. Min Range: -6.4102
Max Act: 5.8165. Min Act: -0.1700
Data Index: 4212841 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4102. Min Range: -6.4102
Max Act: 5.7852. Min Act: -0.1700
Data Index: 2751057 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4102. Min Range: -6.4102
Max Act: 5.7540. Min Act: -0.1700
Data Index: 8333798 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4102. Min Range: -6.4102
Max Act: 5.7227. Min Act: -0.1700
Data Index: 2685480 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4102. Min Range: -6.4102
Max Act: 5.6915. Min Act: -0.1700
Data Index: 56689 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #19