Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1940 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5879. Min Range: -8.5879
Max Act: 8.5879. Min Act: -0.1700
Data Index: 5364755 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5879. Min Range: -8.5879
Max Act: 8.0879. Min Act: -0.1700
Data Index: 7337845 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5879. Min Range: -8.5879
Max Act: 8.0879. Min Act: -0.1700
Data Index: 4759806 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5879. Min Range: -8.5879
Max Act: 8.0254. Min Act: -0.1700
Data Index: 4845576 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5879. Min Range: -8.5879
Max Act: 7.9629. Min Act: -0.1700
Data Index: 4071183 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5879. Min Range: -8.5879
Max Act: 7.9004. Min Act: -0.1700
Data Index: 7759642 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5879. Min Range: -8.5879
Max Act: 7.9629. Min Act: -0.1700
Data Index: 4845759 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5879. Min Range: -8.5879
Max Act: 7.9629. Min Act: -0.1700
Data Index: 1807353 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5879. Min Range: -8.5879
Max Act: 7.9629. Min Act: -0.1700
Data Index: 649467 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5879. Min Range: -8.5879
Max Act: 7.9004. Min Act: -0.1700
Data Index: 5082906 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5879. Min Range: -8.5879
Max Act: 7.9004. Min Act: -0.1700
Data Index: 91395 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5879. Min Range: -8.5879
Max Act: 7.9004. Min Act: -0.1700
Data Index: 6243810 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5879. Min Range: -8.5879
Max Act: 7.9004. Min Act: -0.1700
Data Index: 5909776 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5879. Min Range: -8.5879
Max Act: 7.9004. Min Act: -0.1700
Data Index: 3409013 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5879. Min Range: -8.5879
Max Act: 7.9004. Min Act: -0.1700
Data Index: 2798780 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5879. Min Range: -8.5879
Max Act: 7.8379. Min Act: -0.1700
Data Index: 2195905 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5879. Min Range: -8.5879
Max Act: 7.8379. Min Act: -0.1700
Data Index: 5006231 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5879. Min Range: -8.5879
Max Act: 7.8379. Min Act: -0.1700
Data Index: 7575982 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5879. Min Range: -8.5879
Max Act: 7.8379. Min Act: -0.1700
Data Index: 8426275 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5879. Min Range: -8.5879
Max Act: 7.8379. Min Act: -0.1700
Data Index: 6148286 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19