Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1559 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.9355. Min Act: -0.1700
Data Index: 3697992 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.8417. Min Act: -0.1700
Data Index: 4238494 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.8417. Min Act: -0.1700
Data Index: 2320537 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.8105. Min Act: -0.1700
Data Index: 3574797 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.8417. Min Act: -0.1700
Data Index: 335809 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.6542. Min Act: -0.1700
Data Index: 8576103 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.6855. Min Act: -0.1700
Data Index: 8354658 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.6542. Min Act: -0.1700
Data Index: 1609994 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.5917. Min Act: -0.1700
Data Index: 191866 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.5917. Min Act: -0.1700
Data Index: 7735112 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.5605. Min Act: -0.1700
Data Index: 4348071 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.5605. Min Act: -0.1700
Data Index: 7640239 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.5605. Min Act: -0.1700
Data Index: 2749666 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.4980. Min Act: -0.1700
Data Index: 3983106 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.5292. Min Act: -0.1700
Data Index: 1298986 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.4980. Min Act: -0.1700
Data Index: 298383 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.5292. Min Act: -0.1700
Data Index: 6434055 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.4980. Min Act: -0.1700
Data Index: 3337300 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.4667. Min Act: -0.1700
Data Index: 270699 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9355. Min Range: -4.9355
Max Act: 4.4980. Min Act: -0.1700
Data Index: 1572753 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #19