Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2727 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0208. Min Range: -7.0208
Max Act: 7.0208. Min Act: -0.1700
Data Index: 356930 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0208. Min Range: -7.0208
Max Act: 6.8333. Min Act: -0.1700
Data Index: 356917 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0208. Min Range: -7.0208
Max Act: 6.1146. Min Act: -0.1700
Data Index: 4209635 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0208. Min Range: -7.0208
Max Act: 6.1458. Min Act: -0.1700
Data Index: 229028 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0208. Min Range: -7.0208
Max Act: 6.0521. Min Act: -0.1700
Data Index: 1129847 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0208. Min Range: -7.0208
Max Act: 6.0521. Min Act: -0.1700
Data Index: 3556210 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0208. Min Range: -7.0208
Max Act: 6.0521. Min Act: -0.1700
Data Index: 2730678 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0208. Min Range: -7.0208
Max Act: 5.9896. Min Act: -0.1700
Data Index: 7323909 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0208. Min Range: -7.0208
Max Act: 6.0208. Min Act: -0.1700
Data Index: 8108475 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0208. Min Range: -7.0208
Max Act: 5.9896. Min Act: -0.1700
Data Index: 2893807 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0208. Min Range: -7.0208
Max Act: 5.9583. Min Act: -0.1700
Data Index: 7933324 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0208. Min Range: -7.0208
Max Act: 5.9271. Min Act: -0.1700
Data Index: 6348651 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0208. Min Range: -7.0208
Max Act: 5.9271. Min Act: -0.1700
Data Index: 7533391 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0208. Min Range: -7.0208
Max Act: 5.9271. Min Act: -0.1700
Data Index: 6497622 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0208. Min Range: -7.0208
Max Act: 5.8958. Min Act: -0.1700
Data Index: 3472344 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0208. Min Range: -7.0208
Max Act: 5.8958. Min Act: -0.1700
Data Index: 4509829 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0208. Min Range: -7.0208
Max Act: 5.8958. Min Act: -0.1700
Data Index: 5935536 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0208. Min Range: -7.0208
Max Act: 5.8646. Min Act: -0.1700
Data Index: 1830364 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0208. Min Range: -7.0208
Max Act: 5.8646. Min Act: -0.1700
Data Index: 8296761 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0208. Min Range: -7.0208
Max Act: 5.8021. Min Act: -0.1700
Data Index: 3572704 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #19