Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2375 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.6616. Min Act: -0.1700
Data Index: 5740571 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.5991. Min Act: -0.1700
Data Index: 4263907 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.5366. Min Act: -0.1700
Data Index: 7134006 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.5054. Min Act: -0.1700
Data Index: 1143222 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.4741. Min Act: -0.1700
Data Index: 1415040 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.4741. Min Act: -0.1700
Data Index: 6922432 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.4428. Min Act: -0.1700
Data Index: 7196485 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.4428. Min Act: -0.1700
Data Index: 1494358 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.4428. Min Act: -0.1700
Data Index: 4904142 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.3491. Min Act: -0.1700
Data Index: 7651909 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.3178. Min Act: -0.1700
Data Index: 4453264 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.3178. Min Act: -0.1700
Data Index: 1295896 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.3178. Min Act: -0.1700
Data Index: 7752067 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.2866. Min Act: -0.1700
Data Index: 3608306 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.2866. Min Act: -0.1700
Data Index: 3381334 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.2866. Min Act: -0.1700
Data Index: 268664 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.2553. Min Act: -0.1700
Data Index: 5392074 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.2553. Min Act: -0.1700
Data Index: 2999344 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.2866. Min Act: -0.1700
Data Index: 4901053 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6616. Min Range: -4.6616
Max Act: 4.2553. Min Act: -0.1700
Data Index: 1395747 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19