Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5649 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3083. Min Range: -6.3083
Max Act: 6.3083. Min Act: -0.1700
Data Index: 4916441 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3083. Min Range: -6.3083
Max Act: 6.2146. Min Act: -0.1700
Data Index: 5436231 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3083. Min Range: -6.3083
Max Act: 6.0583. Min Act: -0.1700
Data Index: 3840974 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3083. Min Range: -6.3083
Max Act: 6.0583. Min Act: -0.1700
Data Index: 63244 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3083. Min Range: -6.3083
Max Act: 5.9958. Min Act: -0.1700
Data Index: 2105334 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3083. Min Range: -6.3083
Max Act: 5.9333. Min Act: -0.1700
Data Index: 4506911 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3083. Min Range: -6.3083
Max Act: 5.9333. Min Act: -0.1700
Data Index: 3961457 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3083. Min Range: -6.3083
Max Act: 5.9333. Min Act: -0.1700
Data Index: 4001835 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3083. Min Range: -6.3083
Max Act: 5.9021. Min Act: -0.1700
Data Index: 2307510 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3083. Min Range: -6.3083
Max Act: 5.8708. Min Act: -0.1700
Data Index: 6640774 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3083. Min Range: -6.3083
Max Act: 5.8708. Min Act: -0.1700
Data Index: 8728483 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3083. Min Range: -6.3083
Max Act: 5.8708. Min Act: -0.1700
Data Index: 284779 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3083. Min Range: -6.3083
Max Act: 5.8708. Min Act: -0.1700
Data Index: 5950626 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3083. Min Range: -6.3083
Max Act: 5.8396. Min Act: -0.1700
Data Index: 5907481 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3083. Min Range: -6.3083
Max Act: 5.8396. Min Act: -0.1700
Data Index: 1750391 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3083. Min Range: -6.3083
Max Act: 5.8083. Min Act: -0.1700
Data Index: 7742156 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3083. Min Range: -6.3083
Max Act: 5.8083. Min Act: -0.1700
Data Index: 2063924 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3083. Min Range: -6.3083
Max Act: 5.8083. Min Act: -0.1700
Data Index: 368437 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3083. Min Range: -6.3083
Max Act: 5.7771. Min Act: -0.1700
Data Index: 1307314 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3083. Min Range: -6.3083
Max Act: 5.7771. Min Act: -0.1700
Data Index: 7518076 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19