Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 884 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0504. Min Range: -8.0504
Max Act: 8.0504. Min Act: -0.1700
Data Index: 239504 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0504. Min Range: -8.0504
Max Act: 7.9254. Min Act: -0.1700
Data Index: 2068602 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0504. Min Range: -8.0504
Max Act: 7.8629. Min Act: -0.1700
Data Index: 7012979 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0504. Min Range: -8.0504
Max Act: 7.8941. Min Act: -0.1700
Data Index: 6075072 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0504. Min Range: -8.0504
Max Act: 7.8629. Min Act: -0.1700
Data Index: 4839922 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0504. Min Range: -8.0504
Max Act: 7.8629. Min Act: -0.1700
Data Index: 7967789 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0504. Min Range: -8.0504
Max Act: 7.7691. Min Act: -0.1700
Data Index: 3018998 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0504. Min Range: -8.0504
Max Act: 7.7691. Min Act: -0.1700
Data Index: 3835268 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0504. Min Range: -8.0504
Max Act: 7.7379. Min Act: -0.1700
Data Index: 3409439 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0504. Min Range: -8.0504
Max Act: 7.7066. Min Act: -0.1700
Data Index: 1457981 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0504. Min Range: -8.0504
Max Act: 7.7066. Min Act: -0.1700
Data Index: 1104623 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0504. Min Range: -8.0504
Max Act: 7.7691. Min Act: -0.1700
Data Index: 4638338 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0504. Min Range: -8.0504
Max Act: 7.7066. Min Act: -0.1700
Data Index: 4078482 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0504. Min Range: -8.0504
Max Act: 7.6754. Min Act: -0.1700
Data Index: 3509894 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0504. Min Range: -8.0504
Max Act: 7.7066. Min Act: -0.1700
Data Index: 3190408 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0504. Min Range: -8.0504
Max Act: 7.6754. Min Act: -0.1700
Data Index: 548537 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0504. Min Range: -8.0504
Max Act: 7.6754. Min Act: -0.1700
Data Index: 2917102 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0504. Min Range: -8.0504
Max Act: 7.6441. Min Act: -0.1700
Data Index: 1124891 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0504. Min Range: -8.0504
Max Act: 7.6441. Min Act: -0.1700
Data Index: 5052852 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0504. Min Range: -8.0504
Max Act: 7.6441. Min Act: -0.1700
Data Index: 3672799 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19