Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5021 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5102. Min Range: -7.5102
Max Act: 7.5102. Min Act: -0.1700
Data Index: 8467753 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5102. Min Range: -7.5102
Max Act: 7.1977. Min Act: -0.1700
Data Index: 5221501 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5102. Min Range: -7.5102
Max Act: 7.1977. Min Act: -0.1700
Data Index: 2851307 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5102. Min Range: -7.5102
Max Act: 7.0102. Min Act: -0.1700
Data Index: 1840832 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5102. Min Range: -7.5102
Max Act: 6.9165. Min Act: -0.1700
Data Index: 1835554 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5102. Min Range: -7.5102
Max Act: 6.8540. Min Act: -0.1700
Data Index: 5200961 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5102. Min Range: -7.5102
Max Act: 6.8540. Min Act: -0.1700
Data Index: 455291 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5102. Min Range: -7.5102
Max Act: 6.8540. Min Act: -0.1700
Data Index: 509305 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5102. Min Range: -7.5102
Max Act: 6.7915. Min Act: -0.1700
Data Index: 4416984 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5102. Min Range: -7.5102
Max Act: 6.7915. Min Act: -0.1700
Data Index: 7990788 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5102. Min Range: -7.5102
Max Act: 6.7915. Min Act: -0.1700
Data Index: 6460933 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5102. Min Range: -7.5102
Max Act: 6.7602. Min Act: -0.1700
Data Index: 6293407 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5102. Min Range: -7.5102
Max Act: 6.7602. Min Act: -0.1700
Data Index: 7048020 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5102. Min Range: -7.5102
Max Act: 6.7290. Min Act: -0.1700
Data Index: 7259299 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5102. Min Range: -7.5102
Max Act: 6.7290. Min Act: -0.1700
Data Index: 7791928 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5102. Min Range: -7.5102
Max Act: 6.6977. Min Act: -0.1700
Data Index: 5207878 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5102. Min Range: -7.5102
Max Act: 6.6977. Min Act: -0.1700
Data Index: 3461696 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5102. Min Range: -7.5102
Max Act: 6.6977. Min Act: -0.1700
Data Index: 7616648 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5102. Min Range: -7.5102
Max Act: 6.6977. Min Act: -0.1700
Data Index: 6885602 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5102. Min Range: -7.5102
Max Act: 6.6665. Min Act: -0.1700
Data Index: 4600238 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19