Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2160 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.9439. Min Act: -0.1700
Data Index: 8460435 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.9439. Min Act: -0.1700
Data Index: 7270270 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.9283. Min Act: -0.1700
Data Index: 6630031 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.8814. Min Act: -0.1700
Data Index: 6032542 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.8345. Min Act: -0.1700
Data Index: 5578254 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.8032. Min Act: -0.1700
Data Index: 7352049 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.7563. Min Act: -0.1700
Data Index: 4358358 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.7407. Min Act: -0.1700
Data Index: 5405512 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.7563. Min Act: -0.1700
Data Index: 197886 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.7563. Min Act: -0.1700
Data Index: 4102830 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.7407. Min Act: -0.1700
Data Index: 825615 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.7094. Min Act: -0.1700
Data Index: 5201756 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.6781. Min Act: -0.1700
Data Index: 740564 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.6937. Min Act: -0.1700
Data Index: 46419 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.6624. Min Act: -0.1700
Data Index: 916915 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.6624. Min Act: -0.1700
Data Index: 8096322 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.6468. Min Act: -0.1700
Data Index: 3619555 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.6468. Min Act: -0.1700
Data Index: 1963313 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.6311. Min Act: -0.1700
Data Index: 288746 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.6468. Min Act: -0.1700
Data Index: 7851293 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19