Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4897 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5396. Min Range: -9.5396
Max Act: 9.5396. Min Act: -0.1698
Data Index: 2614619 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5396. Min Range: -9.5396
Max Act: 9.2896. Min Act: -0.1688
Data Index: 3632345 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5396. Min Range: -9.5396
Max Act: 9.1646. Min Act: -0.1700
Data Index: 1676802 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5396. Min Range: -9.5396
Max Act: 8.9771. Min Act: -0.1700
Data Index: 3357469 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5396. Min Range: -9.5396
Max Act: 8.9146. Min Act: -0.1700
Data Index: 6959547 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5396. Min Range: -9.5396
Max Act: 8.9146. Min Act: -0.1700
Data Index: 3678455 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5396. Min Range: -9.5396
Max Act: 8.8521. Min Act: -0.1700
Data Index: 5582793 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5396. Min Range: -9.5396
Max Act: 8.9146. Min Act: -0.1699
Data Index: 8756458 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5396. Min Range: -9.5396
Max Act: 8.8521. Min Act: -0.1700
Data Index: 1028407 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5396. Min Range: -9.5396
Max Act: 8.8521. Min Act: -0.1700
Data Index: 1777712 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5396. Min Range: -9.5396
Max Act: 8.7896. Min Act: -0.1700
Data Index: 4572302 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5396. Min Range: -9.5396
Max Act: 8.7896. Min Act: -0.1695
Data Index: 5220774 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5396. Min Range: -9.5396
Max Act: 8.7896. Min Act: -0.1700
Data Index: 576569 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5396. Min Range: -9.5396
Max Act: 8.7271. Min Act: -0.1700
Data Index: 2793037 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5396. Min Range: -9.5396
Max Act: 8.7271. Min Act: -0.1700
Data Index: 1686087 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5396. Min Range: -9.5396
Max Act: 8.6646. Min Act: -0.1688
Data Index: 6031002 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5396. Min Range: -9.5396
Max Act: 8.7271. Min Act: -0.1700
Data Index: 6090490 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5396. Min Range: -9.5396
Max Act: 8.6646. Min Act: -0.1700
Data Index: 1523851 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5396. Min Range: -9.5396
Max Act: 8.6646. Min Act: -0.1700
Data Index: 3332713 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5396. Min Range: -9.5396
Max Act: 8.6646. Min Act: -0.1700
Data Index: 8654491 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19