Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3443 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0498. Min Range: -4.0498
Max Act: 4.0185. Min Act: -0.1700
Data Index: 5647079 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0498. Min Range: -4.0498
Max Act: 4.0185. Min Act: -0.1700
Data Index: 1629531 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0498. Min Range: -4.0498
Max Act: 4.0498. Min Act: -0.1700
Data Index: 1697187 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0498. Min Range: -4.0498
Max Act: 4.0185. Min Act: -0.1700
Data Index: 8072004 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0498. Min Range: -4.0498
Max Act: 4.0185. Min Act: -0.1700
Data Index: 7231244 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0498. Min Range: -4.0498
Max Act: 3.9560. Min Act: -0.1700
Data Index: 6764876 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0498. Min Range: -4.0498
Max Act: 3.9247. Min Act: -0.1700
Data Index: 2936667 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0498. Min Range: -4.0498
Max Act: 3.9247. Min Act: -0.1700
Data Index: 3190378 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0498. Min Range: -4.0498
Max Act: 3.9560. Min Act: -0.1700
Data Index: 138493 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0498. Min Range: -4.0498
Max Act: 3.9560. Min Act: -0.1700
Data Index: 3944553 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0498. Min Range: -4.0498
Max Act: 3.9560. Min Act: -0.1700
Data Index: 8343699 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0498. Min Range: -4.0498
Max Act: 3.9560. Min Act: -0.1700
Data Index: 2435723 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0498. Min Range: -4.0498
Max Act: 3.9560. Min Act: -0.1700
Data Index: 8059179 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0498. Min Range: -4.0498
Max Act: 3.8622. Min Act: -0.1700
Data Index: 2682667 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0498. Min Range: -4.0498
Max Act: 3.9247. Min Act: -0.1700
Data Index: 5740980 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0498. Min Range: -4.0498
Max Act: 3.9560. Min Act: -0.1700
Data Index: 5627197 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0498. Min Range: -4.0498
Max Act: 3.8622. Min Act: -0.1700
Data Index: 3136814 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0498. Min Range: -4.0498
Max Act: 3.9560. Min Act: -0.1700
Data Index: 5574000 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0498. Min Range: -4.0498
Max Act: 3.9247. Min Act: -0.1700
Data Index: 1626061 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0498. Min Range: -4.0498
Max Act: 3.9247. Min Act: -0.1700
Data Index: 7741134 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19