Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2073 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9885. Min Range: -4.9885
Max Act: 4.9885. Min Act: -0.1700
Data Index: 3509405 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9885. Min Range: -4.9885
Max Act: 4.9572. Min Act: -0.1700
Data Index: 8610885 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9885. Min Range: -4.9885
Max Act: 4.8635. Min Act: -0.1700
Data Index: 105179 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9885. Min Range: -4.9885
Max Act: 4.8635. Min Act: -0.1700
Data Index: 4943322 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9885. Min Range: -4.9885
Max Act: 4.8322. Min Act: -0.1700
Data Index: 1083384 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9885. Min Range: -4.9885
Max Act: 4.8322. Min Act: -0.1700
Data Index: 2504419 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9885. Min Range: -4.9885
Max Act: 4.8010. Min Act: -0.1700
Data Index: 1923560 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9885. Min Range: -4.9885
Max Act: 4.8010. Min Act: -0.1700
Data Index: 4237054 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9885. Min Range: -4.9885
Max Act: 4.7697. Min Act: -0.1700
Data Index: 6463687 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9885. Min Range: -4.9885
Max Act: 4.7697. Min Act: -0.1700
Data Index: 3242812 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9885. Min Range: -4.9885
Max Act: 4.7697. Min Act: -0.1700
Data Index: 3172766 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9885. Min Range: -4.9885
Max Act: 4.7697. Min Act: -0.1700
Data Index: 3936061 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9885. Min Range: -4.9885
Max Act: 4.7385. Min Act: -0.1700
Data Index: 967026 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9885. Min Range: -4.9885
Max Act: 4.7385. Min Act: -0.1700
Data Index: 8078237 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9885. Min Range: -4.9885
Max Act: 4.7072. Min Act: -0.1700
Data Index: 3917368 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9885. Min Range: -4.9885
Max Act: 4.7072. Min Act: -0.1700
Data Index: 7364135 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9885. Min Range: -4.9885
Max Act: 4.7072. Min Act: -0.1700
Data Index: 8299776 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9885. Min Range: -4.9885
Max Act: 4.6760. Min Act: -0.1700
Data Index: 4501486 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9885. Min Range: -4.9885
Max Act: 4.6447. Min Act: -0.1700
Data Index: 6606207 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9885. Min Range: -4.9885
Max Act: 4.6760. Min Act: -0.1700
Data Index: 4419606 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19