Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3312 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3194. Min Range: -6.3194
Max Act: 6.3194. Min Act: -0.1700
Data Index: 4838144 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3194. Min Range: -6.3194
Max Act: 6.2882. Min Act: -0.1700
Data Index: 4608541 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3194. Min Range: -6.3194
Max Act: 6.1632. Min Act: -0.1700
Data Index: 182530 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3194. Min Range: -6.3194
Max Act: 6.1007. Min Act: -0.1700
Data Index: 3777599 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3194. Min Range: -6.3194
Max Act: 6.0694. Min Act: -0.1700
Data Index: 6982125 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3194. Min Range: -6.3194
Max Act: 6.1007. Min Act: -0.1700
Data Index: 3733692 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3194. Min Range: -6.3194
Max Act: 6.0694. Min Act: -0.1700
Data Index: 3149091 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3194. Min Range: -6.3194
Max Act: 6.0382. Min Act: -0.1700
Data Index: 7004321 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3194. Min Range: -6.3194
Max Act: 6.0382. Min Act: -0.1700
Data Index: 1158498 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3194. Min Range: -6.3194
Max Act: 6.0382. Min Act: -0.1700
Data Index: 1680349 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3194. Min Range: -6.3194
Max Act: 6.0694. Min Act: -0.1700
Data Index: 6865077 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3194. Min Range: -6.3194
Max Act: 6.0069. Min Act: -0.1700
Data Index: 4751792 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3194. Min Range: -6.3194
Max Act: 6.0382. Min Act: -0.1700
Data Index: 3385635 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3194. Min Range: -6.3194
Max Act: 5.9444. Min Act: -0.1700
Data Index: 4245054 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3194. Min Range: -6.3194
Max Act: 5.9444. Min Act: -0.1700
Data Index: 5340924 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3194. Min Range: -6.3194
Max Act: 5.9444. Min Act: -0.1700
Data Index: 5369530 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3194. Min Range: -6.3194
Max Act: 5.9132. Min Act: -0.1700
Data Index: 3816206 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3194. Min Range: -6.3194
Max Act: 5.9132. Min Act: -0.1700
Data Index: 3535387 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3194. Min Range: -6.3194
Max Act: 5.9132. Min Act: -0.1700
Data Index: 1870996 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3194. Min Range: -6.3194
Max Act: 5.9132. Min Act: -0.1700
Data Index: 1626393 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #19