Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3555 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2190. Min Range: -3.2190
Max Act: 3.2190. Min Act: -0.1700
Data Index: 3420555 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2190. Min Range: -3.2190
Max Act: 3.2190. Min Act: -0.1700
Data Index: 3456913 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2190. Min Range: -3.2190
Max Act: 3.2033. Min Act: -0.1700
Data Index: 6817766 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2190. Min Range: -3.2190
Max Act: 3.2033. Min Act: -0.1700
Data Index: 1972185 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2190. Min Range: -3.2190
Max Act: 3.2033. Min Act: -0.1700
Data Index: 7907274 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2190. Min Range: -3.2190
Max Act: 3.2033. Min Act: -0.1700
Data Index: 3445639 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2190. Min Range: -3.2190
Max Act: 3.2033. Min Act: -0.1700
Data Index: 5980775 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2190. Min Range: -3.2190
Max Act: 3.2033. Min Act: -0.1700
Data Index: 4507449 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2190. Min Range: -3.2190
Max Act: 3.2033. Min Act: -0.1700
Data Index: 45108 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2190. Min Range: -3.2190
Max Act: 3.1875. Min Act: -0.1700
Data Index: 1864170 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2190. Min Range: -3.2190
Max Act: 3.1875. Min Act: -0.1700
Data Index: 5645737 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2190. Min Range: -3.2190
Max Act: 3.1875. Min Act: -0.1700
Data Index: 4817381 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2190. Min Range: -3.2190
Max Act: 3.1875. Min Act: -0.1700
Data Index: 7476334 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2190. Min Range: -3.2190
Max Act: 3.1718. Min Act: -0.1700
Data Index: 5659470 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2190. Min Range: -3.2190
Max Act: 3.1718. Min Act: -0.1700
Data Index: 5854860 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2190. Min Range: -3.2190
Max Act: 3.1718. Min Act: -0.1700
Data Index: 3198222 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2190. Min Range: -3.2190
Max Act: 3.1718. Min Act: -0.1700
Data Index: 2768325 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2190. Min Range: -3.2190
Max Act: 3.1718. Min Act: -0.1700
Data Index: 2300287 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2190. Min Range: -3.2190
Max Act: 3.1718. Min Act: -0.1700
Data Index: 6082364 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2190. Min Range: -3.2190
Max Act: 3.1718. Min Act: -0.1700
Data Index: 6185546 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19