Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 909 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.6363. Min Range: -11.6363
Max Act: 11.6363. Min Act: -0.1700
Data Index: 606028 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.6363. Min Range: -11.6363
Max Act: 11.6363. Min Act: -0.1700
Data Index: 8515731 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.6363. Min Range: -11.6363
Max Act: 11.3863. Min Act: -0.1700
Data Index: 810003 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.6363. Min Range: -11.6363
Max Act: 11.3238. Min Act: -0.1699
Data Index: 8291056 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.6363. Min Range: -11.6363
Max Act: 11.3238. Min Act: -0.1700
Data Index: 4214984 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.6363. Min Range: -11.6363
Max Act: 11.3238. Min Act: -0.1700
Data Index: 1059763 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.6363. Min Range: -11.6363
Max Act: 11.2613. Min Act: -0.1700
Data Index: 3426031 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.6363. Min Range: -11.6363
Max Act: 11.1988. Min Act: -0.1700
Data Index: 6952300 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.6363. Min Range: -11.6363
Max Act: 11.1363. Min Act: -0.1700
Data Index: 1693618 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.6363. Min Range: -11.6363
Max Act: 11.1363. Min Act: -0.1697
Data Index: 2721439 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.6363. Min Range: -11.6363
Max Act: 11.0738. Min Act: -0.1700
Data Index: 6525625 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.6363. Min Range: -11.6363
Max Act: 11.0738. Min Act: -0.1699
Data Index: 1507029 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.6363. Min Range: -11.6363
Max Act: 11.0738. Min Act: -0.1700
Data Index: 3554349 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.6363. Min Range: -11.6363
Max Act: 11.0738. Min Act: -0.1700
Data Index: 330908 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.6363. Min Range: -11.6363
Max Act: 11.0738. Min Act: -0.1700
Data Index: 245404 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.6363. Min Range: -11.6363
Max Act: 11.0113. Min Act: -0.1700
Data Index: 8010573 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.6363. Min Range: -11.6363
Max Act: 10.9488. Min Act: -0.1698
Data Index: 1848563 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.6363. Min Range: -11.6363
Max Act: 10.9488. Min Act: -0.1700
Data Index: 2215783 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.6363. Min Range: -11.6363
Max Act: 10.8863. Min Act: -0.1700
Data Index: 1018133 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.6363. Min Range: -11.6363
Max Act: 10.9488. Min Act: -0.1700
Data Index: 3422168 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19