Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4808 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6117. Min Range: -5.6117
Max Act: 5.6117. Min Act: -0.1700
Data Index: 2205968 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6117. Min Range: -5.6117
Max Act: 5.6117. Min Act: -0.1700
Data Index: 5895570 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6117. Min Range: -5.6117
Max Act: 5.5179. Min Act: -0.1700
Data Index: 1018276 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6117. Min Range: -5.6117
Max Act: 5.4867. Min Act: -0.1700
Data Index: 4793876 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6117. Min Range: -5.6117
Max Act: 5.3929. Min Act: -0.1700
Data Index: 8320116 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6117. Min Range: -5.6117
Max Act: 5.4242. Min Act: -0.1700
Data Index: 539924 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6117. Min Range: -5.6117
Max Act: 5.3929. Min Act: -0.1700
Data Index: 8437509 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6117. Min Range: -5.6117
Max Act: 5.3929. Min Act: -0.1700
Data Index: 1223966 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6117. Min Range: -5.6117
Max Act: 5.3929. Min Act: -0.1700
Data Index: 842771 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6117. Min Range: -5.6117
Max Act: 5.3304. Min Act: -0.1700
Data Index: 6679403 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6117. Min Range: -5.6117
Max Act: 5.3617. Min Act: -0.1700
Data Index: 5021005 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6117. Min Range: -5.6117
Max Act: 5.3304. Min Act: -0.1700
Data Index: 1054000 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6117. Min Range: -5.6117
Max Act: 5.3617. Min Act: -0.1700
Data Index: 8517350 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6117. Min Range: -5.6117
Max Act: 5.3929. Min Act: -0.1700
Data Index: 1625693 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6117. Min Range: -5.6117
Max Act: 5.3617. Min Act: -0.1700
Data Index: 3207679 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6117. Min Range: -5.6117
Max Act: 5.3617. Min Act: -0.1700
Data Index: 2727092 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6117. Min Range: -5.6117
Max Act: 5.3304. Min Act: -0.1700
Data Index: 8145494 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6117. Min Range: -5.6117
Max Act: 5.2992. Min Act: -0.1700
Data Index: 5001101 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6117. Min Range: -5.6117
Max Act: 5.2679. Min Act: -0.1700
Data Index: 2066258 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6117. Min Range: -5.6117
Max Act: 5.2992. Min Act: -0.1700
Data Index: 3765129 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19