Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4082 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6109. Min Range: -9.6109
Max Act: 9.6109. Min Act: -0.1700
Data Index: 7751730 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6109. Min Range: -9.6109
Max Act: 9.4859. Min Act: -0.1700
Data Index: 7471445 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6109. Min Range: -9.6109
Max Act: 9.3609. Min Act: -0.1700
Data Index: 3769024 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6109. Min Range: -9.6109
Max Act: 9.2984. Min Act: -0.1700
Data Index: 8460385 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6109. Min Range: -9.6109
Max Act: 9.2984. Min Act: -0.1700
Data Index: 239431 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6109. Min Range: -9.6109
Max Act: 9.2984. Min Act: -0.1700
Data Index: 7795857 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6109. Min Range: -9.6109
Max Act: 9.1109. Min Act: -0.1700
Data Index: 1361784 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6109. Min Range: -9.6109
Max Act: 9.1109. Min Act: -0.1700
Data Index: 2535737 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6109. Min Range: -9.6109
Max Act: 9.1109. Min Act: -0.1700
Data Index: 3758645 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6109. Min Range: -9.6109
Max Act: 9.0484. Min Act: -0.1700
Data Index: 15463 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6109. Min Range: -9.6109
Max Act: 9.0484. Min Act: -0.1700
Data Index: 3682306 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6109. Min Range: -9.6109
Max Act: 8.9859. Min Act: -0.1700
Data Index: 3763756 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6109. Min Range: -9.6109
Max Act: 8.9859. Min Act: -0.1700
Data Index: 2614389 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6109. Min Range: -9.6109
Max Act: 8.8609. Min Act: -0.1700
Data Index: 7160817 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6109. Min Range: -9.6109
Max Act: 8.9234. Min Act: -0.1700
Data Index: 1027607 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6109. Min Range: -9.6109
Max Act: 8.9234. Min Act: -0.1700
Data Index: 3114271 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6109. Min Range: -9.6109
Max Act: 8.9234. Min Act: -0.1700
Data Index: 3676686 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6109. Min Range: -9.6109
Max Act: 8.8609. Min Act: -0.1700
Data Index: 5244123 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6109. Min Range: -9.6109
Max Act: 8.8609. Min Act: -0.1700
Data Index: 7062569 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6109. Min Range: -9.6109
Max Act: 8.7984. Min Act: -0.1700
Data Index: 1718681 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19