Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4574 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.5905. Min Act: -0.1700
Data Index: 2673650 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.4655. Min Act: -0.1700
Data Index: 7268563 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.4655. Min Act: -0.1700
Data Index: 3928947 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.4655. Min Act: -0.1700
Data Index: 8394036 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.4342. Min Act: -0.1700
Data Index: 5685276 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.4030. Min Act: -0.1700
Data Index: 3674442 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.3405. Min Act: -0.1700
Data Index: 4408933 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.3405. Min Act: -0.1700
Data Index: 6926982 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.3092. Min Act: -0.1700
Data Index: 8058940 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.3092. Min Act: -0.1700
Data Index: 8650700 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.3092. Min Act: -0.1700
Data Index: 2611218 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.3092. Min Act: -0.1700
Data Index: 128499 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.3092. Min Act: -0.1700
Data Index: 4875901 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.3405. Min Act: -0.1700
Data Index: 5715440 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.3092. Min Act: -0.1700
Data Index: 1987996 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.2780. Min Act: -0.1700
Data Index: 581805 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.2467. Min Act: -0.1700
Data Index: 1858980 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.2155. Min Act: -0.1700
Data Index: 743338 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.2155. Min Act: -0.1700
Data Index: 3779529 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.2155. Min Act: -0.1700
Data Index: 2900251 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #19