Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5244 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.7188. Min Act: -0.1700
Data Index: 7127555 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.6875. Min Act: -0.1700
Data Index: 5190156 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.6250. Min Act: -0.1700
Data Index: 3538731 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.6563. Min Act: -0.1700
Data Index: 7773423 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.5938. Min Act: -0.1700
Data Index: 3748472 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.5625. Min Act: -0.1700
Data Index: 8294867 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.5625. Min Act: -0.1700
Data Index: 1091168 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.5625. Min Act: -0.1700
Data Index: 1900805 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.5625. Min Act: -0.1700
Data Index: 7127557 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.5313. Min Act: -0.1700
Data Index: 2107684 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.5000. Min Act: -0.1700
Data Index: 3538727 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.5000. Min Act: -0.1700
Data Index: 8483380 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.5000. Min Act: -0.1700
Data Index: 1256248 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.4375. Min Act: -0.1700
Data Index: 5493976 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.4375. Min Act: -0.1700
Data Index: 894330 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.4375. Min Act: -0.1700
Data Index: 5145482 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.4688. Min Act: -0.1700
Data Index: 324114 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.4375. Min Act: -0.1700
Data Index: 8305497 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.3750. Min Act: -0.1700
Data Index: 558286 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7188. Min Range: -5.7188
Max Act: 5.4063. Min Act: -0.1700
Data Index: 1395087 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #19