Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1875 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8419. Min Range: -8.8419
Max Act: 8.8419. Min Act: -0.1700
Data Index: 8765195 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8419. Min Range: -8.8419
Max Act: 8.4669. Min Act: -0.1700
Data Index: 3010123 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8419. Min Range: -8.8419
Max Act: 8.3419. Min Act: -0.1700
Data Index: 3500752 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8419. Min Range: -8.8419
Max Act: 8.3106. Min Act: -0.1700
Data Index: 4198597 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8419. Min Range: -8.8419
Max Act: 8.2169. Min Act: -0.1700
Data Index: 5541063 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8419. Min Range: -8.8419
Max Act: 8.1856. Min Act: -0.1700
Data Index: 1459621 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8419. Min Range: -8.8419
Max Act: 8.1544. Min Act: -0.1700
Data Index: 3379784 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8419. Min Range: -8.8419
Max Act: 8.1544. Min Act: -0.1700
Data Index: 1490976 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8419. Min Range: -8.8419
Max Act: 8.1544. Min Act: -0.1700
Data Index: 6607895 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8419. Min Range: -8.8419
Max Act: 8.1231. Min Act: -0.1700
Data Index: 6421863 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8419. Min Range: -8.8419
Max Act: 8.0919. Min Act: -0.1700
Data Index: 5279714 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8419. Min Range: -8.8419
Max Act: 8.0919. Min Act: -0.1700
Data Index: 1079862 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8419. Min Range: -8.8419
Max Act: 8.0606. Min Act: -0.1700
Data Index: 922380 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8419. Min Range: -8.8419
Max Act: 8.0606. Min Act: -0.1700
Data Index: 746498 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8419. Min Range: -8.8419
Max Act: 8.0606. Min Act: -0.1700
Data Index: 1774809 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8419. Min Range: -8.8419
Max Act: 8.0294. Min Act: -0.1700
Data Index: 3204436 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8419. Min Range: -8.8419
Max Act: 7.9669. Min Act: -0.1700
Data Index: 159275 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8419. Min Range: -8.8419
Max Act: 7.9981. Min Act: -0.1700
Data Index: 4349488 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8419. Min Range: -8.8419
Max Act: 7.9356. Min Act: -0.1700
Data Index: 7894346 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8419. Min Range: -8.8419
Max Act: 7.8419. Min Act: -0.1700
Data Index: 2113066 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19