Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 800 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9826. Min Range: -3.9826
Max Act: 3.9826. Min Act: -0.1700
Data Index: 4333258 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9826. Min Range: -3.9826
Max Act: 3.9513. Min Act: -0.1700
Data Index: 2698297 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9826. Min Range: -3.9826
Max Act: 3.9513. Min Act: -0.1700
Data Index: 389404 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9826. Min Range: -3.9826
Max Act: 3.9200. Min Act: -0.1700
Data Index: 1906633 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9826. Min Range: -3.9826
Max Act: 3.9200. Min Act: -0.1700
Data Index: 7166391 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9826. Min Range: -3.9826
Max Act: 3.9200. Min Act: -0.1700
Data Index: 3032494 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9826. Min Range: -3.9826
Max Act: 3.8575. Min Act: -0.1700
Data Index: 248331 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9826. Min Range: -3.9826
Max Act: 3.8575. Min Act: -0.1700
Data Index: 857648 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9826. Min Range: -3.9826
Max Act: 3.8262. Min Act: -0.1700
Data Index: 4689493 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9826. Min Range: -3.9826
Max Act: 3.7950. Min Act: -0.1700
Data Index: 7037533 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9826. Min Range: -3.9826
Max Act: 3.7637. Min Act: -0.1700
Data Index: 680243 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9826. Min Range: -3.9826
Max Act: 3.7950. Min Act: -0.1700
Data Index: 1035225 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9826. Min Range: -3.9826
Max Act: 3.7637. Min Act: -0.1700
Data Index: 2203978 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9826. Min Range: -3.9826
Max Act: 3.7637. Min Act: -0.1700
Data Index: 4974247 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9826. Min Range: -3.9826
Max Act: 3.7637. Min Act: -0.1700
Data Index: 2752917 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9826. Min Range: -3.9826
Max Act: 3.7637. Min Act: -0.1700
Data Index: 7991520 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9826. Min Range: -3.9826
Max Act: 3.7324. Min Act: -0.1700
Data Index: 2836788 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9826. Min Range: -3.9826
Max Act: 3.7324. Min Act: -0.1700
Data Index: 7409272 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9826. Min Range: -3.9826
Max Act: 3.7324. Min Act: -0.1700
Data Index: 3092482 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9826. Min Range: -3.9826
Max Act: 3.7324. Min Act: -0.1700
Data Index: 3443365 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #19