Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 681 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.7259. Min Act: -0.1700
Data Index: 1880177 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.6633. Min Act: -0.1700
Data Index: 8360233 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.5694. Min Act: -0.1700
Data Index: 97769 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.5694. Min Act: -0.1700
Data Index: 7324927 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.5381. Min Act: -0.1700
Data Index: 4320816 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.5068. Min Act: -0.1700
Data Index: 6288623 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.5068. Min Act: -0.1700
Data Index: 1468167 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.5068. Min Act: -0.1700
Data Index: 6236665 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.4755. Min Act: -0.1700
Data Index: 4234594 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.4755. Min Act: -0.1700
Data Index: 1994231 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.4911. Min Act: -0.1700
Data Index: 462225 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.4598. Min Act: -0.1700
Data Index: 8756323 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.4911. Min Act: -0.1700
Data Index: 2229463 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.4598. Min Act: -0.1700
Data Index: 4625170 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.4598. Min Act: -0.1700
Data Index: 1416484 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.4755. Min Act: -0.1700
Data Index: 2480319 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.4755. Min Act: -0.1700
Data Index: 2432278 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.4285. Min Act: -0.1700
Data Index: 3260436 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.4441. Min Act: -0.1700
Data Index: 4151562 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7259. Min Range: -3.7259
Max Act: 3.4441. Min Act: -0.1700
Data Index: 369125 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19