Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4397 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0779. Min Range: -6.0779
Max Act: 6.0779. Min Act: -0.1700
Data Index: 8482928 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0779. Min Range: -6.0779
Max Act: 5.9842. Min Act: -0.1700
Data Index: 686335 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0779. Min Range: -6.0779
Max Act: 5.9529. Min Act: -0.1700
Data Index: 579509 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0779. Min Range: -6.0779
Max Act: 5.8904. Min Act: -0.1700
Data Index: 6798560 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0779. Min Range: -6.0779
Max Act: 5.8592. Min Act: -0.1700
Data Index: 2315781 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0779. Min Range: -6.0779
Max Act: 5.8279. Min Act: -0.1700
Data Index: 6064477 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0779. Min Range: -6.0779
Max Act: 5.8279. Min Act: -0.1700
Data Index: 4127850 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0779. Min Range: -6.0779
Max Act: 5.7967. Min Act: -0.1700
Data Index: 1066799 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0779. Min Range: -6.0779
Max Act: 5.7967. Min Act: -0.1700
Data Index: 5461377 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0779. Min Range: -6.0779
Max Act: 5.7029. Min Act: -0.1700
Data Index: 6483574 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0779. Min Range: -6.0779
Max Act: 5.7342. Min Act: -0.1700
Data Index: 5153215 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0779. Min Range: -6.0779
Max Act: 5.7029. Min Act: -0.1700
Data Index: 6743761 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0779. Min Range: -6.0779
Max Act: 5.6717. Min Act: -0.1700
Data Index: 301971 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0779. Min Range: -6.0779
Max Act: 5.6717. Min Act: -0.1700
Data Index: 5174580 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0779. Min Range: -6.0779
Max Act: 5.6717. Min Act: -0.1700
Data Index: 1810549 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0779. Min Range: -6.0779
Max Act: 5.6404. Min Act: -0.1700
Data Index: 4447804 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0779. Min Range: -6.0779
Max Act: 5.6404. Min Act: -0.1700
Data Index: 3679476 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0779. Min Range: -6.0779
Max Act: 5.6404. Min Act: -0.1700
Data Index: 3679482 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0779. Min Range: -6.0779
Max Act: 5.6717. Min Act: -0.1700
Data Index: 2010023 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0779. Min Range: -6.0779
Max Act: 5.6092. Min Act: -0.1700
Data Index: 3927647 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #19