Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5845 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8969. Min Range: -6.8969
Max Act: 6.8969. Min Act: -0.1700
Data Index: 154911 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8969. Min Range: -6.8969
Max Act: 6.8344. Min Act: -0.1700
Data Index: 5979516 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8969. Min Range: -6.8969
Max Act: 6.8031. Min Act: -0.1700
Data Index: 3392237 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8969. Min Range: -6.8969
Max Act: 6.7719. Min Act: -0.1700
Data Index: 3801157 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8969. Min Range: -6.8969
Max Act: 6.6781. Min Act: -0.1700
Data Index: 1787793 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8969. Min Range: -6.8969
Max Act: 6.6469. Min Act: -0.1700
Data Index: 7714174 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8969. Min Range: -6.8969
Max Act: 6.6469. Min Act: -0.1700
Data Index: 5020375 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8969. Min Range: -6.8969
Max Act: 6.6156. Min Act: -0.1700
Data Index: 4363152 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8969. Min Range: -6.8969
Max Act: 6.6469. Min Act: -0.1700
Data Index: 8070019 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8969. Min Range: -6.8969
Max Act: 6.6156. Min Act: -0.1700
Data Index: 4271172 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8969. Min Range: -6.8969
Max Act: 6.6156. Min Act: -0.1700
Data Index: 2196519 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8969. Min Range: -6.8969
Max Act: 6.6156. Min Act: -0.1700
Data Index: 4357156 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8969. Min Range: -6.8969
Max Act: 6.6469. Min Act: -0.1700
Data Index: 1256697 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8969. Min Range: -6.8969
Max Act: 6.5531. Min Act: -0.1700
Data Index: 3358321 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8969. Min Range: -6.8969
Max Act: 6.5531. Min Act: -0.1700
Data Index: 4251187 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8969. Min Range: -6.8969
Max Act: 6.5844. Min Act: -0.1700
Data Index: 7923453 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8969. Min Range: -6.8969
Max Act: 6.5531. Min Act: -0.1700
Data Index: 5096899 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8969. Min Range: -6.8969
Max Act: 6.5844. Min Act: -0.1700
Data Index: 114843 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8969. Min Range: -6.8969
Max Act: 6.5219. Min Act: -0.1700
Data Index: 2922689 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8969. Min Range: -6.8969
Max Act: 6.5219. Min Act: -0.1700
Data Index: 5391483 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19