Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4972 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6071. Min Range: -5.6071
Max Act: 5.6071. Min Act: -0.1700
Data Index: 3340672 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6071. Min Range: -5.6071
Max Act: 5.5134. Min Act: -0.1700
Data Index: 2921049 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6071. Min Range: -5.6071
Max Act: 5.3571. Min Act: -0.1700
Data Index: 7746546 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6071. Min Range: -5.6071
Max Act: 5.3571. Min Act: -0.1700
Data Index: 3426762 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6071. Min Range: -5.6071
Max Act: 5.3884. Min Act: -0.1700
Data Index: 651904 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6071. Min Range: -5.6071
Max Act: 5.3259. Min Act: -0.1700
Data Index: 7430160 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6071. Min Range: -5.6071
Max Act: 5.2946. Min Act: -0.1700
Data Index: 2705653 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6071. Min Range: -5.6071
Max Act: 5.2946. Min Act: -0.1700
Data Index: 8404972 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6071. Min Range: -5.6071
Max Act: 5.2634. Min Act: -0.1700
Data Index: 8299265 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6071. Min Range: -5.6071
Max Act: 5.2634. Min Act: -0.1700
Data Index: 6314700 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6071. Min Range: -5.6071
Max Act: 5.2634. Min Act: -0.1700
Data Index: 901654 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6071. Min Range: -5.6071
Max Act: 5.2634. Min Act: -0.1700
Data Index: 4466114 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6071. Min Range: -5.6071
Max Act: 5.2009. Min Act: -0.1700
Data Index: 4927238 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6071. Min Range: -5.6071
Max Act: 5.2009. Min Act: -0.1699
Data Index: 3505543 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6071. Min Range: -5.6071
Max Act: 5.2009. Min Act: -0.1700
Data Index: 8134553 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6071. Min Range: -5.6071
Max Act: 5.2009. Min Act: -0.1700
Data Index: 3389001 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6071. Min Range: -5.6071
Max Act: 5.1696. Min Act: -0.1700
Data Index: 290601 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6071. Min Range: -5.6071
Max Act: 5.1696. Min Act: -0.1700
Data Index: 8311110 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6071. Min Range: -5.6071
Max Act: 5.1696. Min Act: -0.1700
Data Index: 1575929 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6071. Min Range: -5.6071
Max Act: 5.1696. Min Act: -0.1700
Data Index: 4354789 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #19