Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4348 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7392. Min Range: -5.7392
Max Act: 5.7392. Min Act: -0.1700
Data Index: 8642141 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7392. Min Range: -5.7392
Max Act: 5.4892. Min Act: -0.1700
Data Index: 3628754 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7392. Min Range: -5.7392
Max Act: 5.4580. Min Act: -0.1700
Data Index: 6671743 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7392. Min Range: -5.7392
Max Act: 5.4892. Min Act: -0.1700
Data Index: 5944906 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7392. Min Range: -5.7392
Max Act: 5.4580. Min Act: -0.1700
Data Index: 4151943 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7392. Min Range: -5.7392
Max Act: 5.3955. Min Act: -0.1700
Data Index: 3340770 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7392. Min Range: -5.7392
Max Act: 5.4580. Min Act: -0.1700
Data Index: 2712968 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7392. Min Range: -5.7392
Max Act: 5.3955. Min Act: -0.1700
Data Index: 5882304 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7392. Min Range: -5.7392
Max Act: 5.3955. Min Act: -0.1700
Data Index: 3779235 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7392. Min Range: -5.7392
Max Act: 5.3642. Min Act: -0.1700
Data Index: 2068641 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7392. Min Range: -5.7392
Max Act: 5.3330. Min Act: -0.1700
Data Index: 7586259 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7392. Min Range: -5.7392
Max Act: 5.3330. Min Act: -0.1700
Data Index: 1401769 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7392. Min Range: -5.7392
Max Act: 5.3330. Min Act: -0.1700
Data Index: 5492272 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7392. Min Range: -5.7392
Max Act: 5.3017. Min Act: -0.1700
Data Index: 4421411 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7392. Min Range: -5.7392
Max Act: 5.3017. Min Act: -0.1700
Data Index: 5891540 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7392. Min Range: -5.7392
Max Act: 5.3017. Min Act: -0.1700
Data Index: 5245622 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7392. Min Range: -5.7392
Max Act: 5.3330. Min Act: -0.1700
Data Index: 5824159 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7392. Min Range: -5.7392
Max Act: 5.2705. Min Act: -0.1700
Data Index: 4710459 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7392. Min Range: -5.7392
Max Act: 5.2705. Min Act: -0.1700
Data Index: 4259607 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7392. Min Range: -5.7392
Max Act: 5.2705. Min Act: -0.1700
Data Index: 997203 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19