Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5522 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5852. Min Range: -5.5852
Max Act: 5.5852. Min Act: -0.1700
Data Index: 605859 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5852. Min Range: -5.5852
Max Act: 5.2415. Min Act: -0.1700
Data Index: 2088610 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5852. Min Range: -5.5852
Max Act: 5.0852. Min Act: -0.1700
Data Index: 7446985 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5852. Min Range: -5.5852
Max Act: 4.9290. Min Act: -0.1700
Data Index: 4688855 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5852. Min Range: -5.5852
Max Act: 4.8352. Min Act: -0.1700
Data Index: 7505631 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5852. Min Range: -5.5852
Max Act: 4.8352. Min Act: -0.1700
Data Index: 8587779 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5852. Min Range: -5.5852
Max Act: 4.8040. Min Act: -0.1700
Data Index: 7410455 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5852. Min Range: -5.5852
Max Act: 4.8040. Min Act: -0.1700
Data Index: 6209535 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5852. Min Range: -5.5852
Max Act: 4.8040. Min Act: -0.1700
Data Index: 2967620 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5852. Min Range: -5.5852
Max Act: 4.7727. Min Act: -0.1700
Data Index: 2681116 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5852. Min Range: -5.5852
Max Act: 4.7727. Min Act: -0.1700
Data Index: 6222371 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5852. Min Range: -5.5852
Max Act: 4.7415. Min Act: -0.1700
Data Index: 2506358 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5852. Min Range: -5.5852
Max Act: 4.7415. Min Act: -0.1700
Data Index: 4829376 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5852. Min Range: -5.5852
Max Act: 4.7415. Min Act: -0.1700
Data Index: 2788429 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5852. Min Range: -5.5852
Max Act: 4.7102. Min Act: -0.1700
Data Index: 3047948 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5852. Min Range: -5.5852
Max Act: 4.7102. Min Act: -0.1700
Data Index: 8224891 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5852. Min Range: -5.5852
Max Act: 4.7102. Min Act: -0.1700
Data Index: 6928705 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5852. Min Range: -5.5852
Max Act: 4.7102. Min Act: -0.1700
Data Index: 3718854 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5852. Min Range: -5.5852
Max Act: 4.7102. Min Act: -0.1700
Data Index: 8107492 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5852. Min Range: -5.5852
Max Act: 4.7102. Min Act: -0.1700
Data Index: 4305054 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19