Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1200 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0504. Min Range: -10.0504
Max Act: 10.0504. Min Act: -0.1700
Data Index: 4009381 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0504. Min Range: -10.0504
Max Act: 10.0504. Min Act: -0.1700
Data Index: 5860161 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0504. Min Range: -10.0504
Max Act: 10.0504. Min Act: -0.1700
Data Index: 7127190 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0504. Min Range: -10.0504
Max Act: 9.9879. Min Act: -0.1700
Data Index: 2719602 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0504. Min Range: -10.0504
Max Act: 9.9254. Min Act: -0.1700
Data Index: 2410825 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0504. Min Range: -10.0504
Max Act: 9.9254. Min Act: -0.1700
Data Index: 6359702 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0504. Min Range: -10.0504
Max Act: 9.8629. Min Act: -0.1700
Data Index: 6072679 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0504. Min Range: -10.0504
Max Act: 9.8629. Min Act: -0.1700
Data Index: 5648814 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0504. Min Range: -10.0504
Max Act: 9.8004. Min Act: -0.1700
Data Index: 7339566 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0504. Min Range: -10.0504
Max Act: 9.7379. Min Act: -0.1700
Data Index: 513369 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0504. Min Range: -10.0504
Max Act: 9.7379. Min Act: -0.1700
Data Index: 7424007 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0504. Min Range: -10.0504
Max Act: 9.7379. Min Act: -0.1700
Data Index: 6344153 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0504. Min Range: -10.0504
Max Act: 9.7379. Min Act: -0.1700
Data Index: 6566987 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0504. Min Range: -10.0504
Max Act: 9.7379. Min Act: -0.1700
Data Index: 7055492 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0504. Min Range: -10.0504
Max Act: 9.6754. Min Act: -0.1700
Data Index: 6930351 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0504. Min Range: -10.0504
Max Act: 9.6129. Min Act: -0.1700
Data Index: 4825927 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0504. Min Range: -10.0504
Max Act: 9.6129. Min Act: -0.1700
Data Index: 4528670 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0504. Min Range: -10.0504
Max Act: 9.6129. Min Act: -0.1700
Data Index: 2726144 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0504. Min Range: -10.0504
Max Act: 9.5504. Min Act: -0.1700
Data Index: 867851 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0504. Min Range: -10.0504
Max Act: 9.5504. Min Act: -0.1700
Data Index: 3789542 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19