Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3486 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.9857. Min Act: -0.1700
Data Index: 4904969 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.9857. Min Act: -0.1700
Data Index: 4454602 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.8919. Min Act: -0.1700
Data Index: 4800733 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.8607. Min Act: -0.1700
Data Index: 5152207 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.8294. Min Act: -0.1700
Data Index: 4726391 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.8294. Min Act: -0.1700
Data Index: 4842449 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.8294. Min Act: -0.1700
Data Index: 1663361 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.8294. Min Act: -0.1700
Data Index: 5459917 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.7982. Min Act: -0.1700
Data Index: 441043 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.7982. Min Act: -0.1700
Data Index: 8437756 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.7982. Min Act: -0.1700
Data Index: 6702991 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.7982. Min Act: -0.1700
Data Index: 1298709 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.7357. Min Act: -0.1700
Data Index: 2413335 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.7357. Min Act: -0.1700
Data Index: 1831929 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.7669. Min Act: -0.1700
Data Index: 6563585 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.7357. Min Act: -0.1700
Data Index: 6998124 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.7982. Min Act: -0.1700
Data Index: 5007361 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.7669. Min Act: -0.1700
Data Index: 1850608 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.7669. Min Act: -0.1700
Data Index: 1187193 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9857. Min Range: -5.9857
Max Act: 5.7669. Min Act: -0.1700
Data Index: 300287 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19