Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 502 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3688. Min Range: -6.3688
Max Act: 6.3688. Min Act: -0.1700
Data Index: 1551876 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3688. Min Range: -6.3688
Max Act: 6.1188. Min Act: -0.1700
Data Index: 3332191 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3688. Min Range: -6.3688
Max Act: 6.0250. Min Act: -0.1700
Data Index: 6733635 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3688. Min Range: -6.3688
Max Act: 6.0563. Min Act: -0.1700
Data Index: 7166905 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3688. Min Range: -6.3688
Max Act: 5.9938. Min Act: -0.1700
Data Index: 6821189 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3688. Min Range: -6.3688
Max Act: 5.9938. Min Act: -0.1700
Data Index: 8534474 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3688. Min Range: -6.3688
Max Act: 5.9625. Min Act: -0.1700
Data Index: 5025760 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3688. Min Range: -6.3688
Max Act: 5.9625. Min Act: -0.1700
Data Index: 6026264 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3688. Min Range: -6.3688
Max Act: 5.9313. Min Act: -0.1700
Data Index: 3230711 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3688. Min Range: -6.3688
Max Act: 5.9625. Min Act: -0.1700
Data Index: 6677218 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3688. Min Range: -6.3688
Max Act: 5.8688. Min Act: -0.1700
Data Index: 6677220 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3688. Min Range: -6.3688
Max Act: 5.9000. Min Act: -0.1700
Data Index: 6483598 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3688. Min Range: -6.3688
Max Act: 5.9000. Min Act: -0.1700
Data Index: 6677219 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3688. Min Range: -6.3688
Max Act: 5.8375. Min Act: -0.1700
Data Index: 286011 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3688. Min Range: -6.3688
Max Act: 5.8688. Min Act: -0.1700
Data Index: 8550679 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3688. Min Range: -6.3688
Max Act: 5.8688. Min Act: -0.1700
Data Index: 3357757 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3688. Min Range: -6.3688
Max Act: 5.8375. Min Act: -0.1700
Data Index: 1381042 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3688. Min Range: -6.3688
Max Act: 5.8063. Min Act: -0.1700
Data Index: 4017129 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3688. Min Range: -6.3688
Max Act: 5.8375. Min Act: -0.1700
Data Index: 3346462 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3688. Min Range: -6.3688
Max Act: 5.8375. Min Act: -0.1700
Data Index: 2803108 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19