Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 633 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8825. Min Range: -2.8825
Max Act: 2.8825. Min Act: -0.1700
Data Index: 370507 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8825. Min Range: -2.8825
Max Act: 2.8667. Min Act: -0.1700
Data Index: 4505416 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8825. Min Range: -2.8825
Max Act: 2.8667. Min Act: -0.1700
Data Index: 54331 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8825. Min Range: -2.8825
Max Act: 2.7871. Min Act: -0.1700
Data Index: 6625804 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8825. Min Range: -2.8825
Max Act: 2.7871. Min Act: -0.1700
Data Index: 363475 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8825. Min Range: -2.8825
Max Act: 2.7871. Min Act: -0.1700
Data Index: 4155890 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8825. Min Range: -2.8825
Max Act: 2.7871. Min Act: -0.1700
Data Index: 94749 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8825. Min Range: -2.8825
Max Act: 2.7871. Min Act: -0.1700
Data Index: 1583614 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8825. Min Range: -2.8825
Max Act: 2.7871. Min Act: -0.1700
Data Index: 6591327 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8825. Min Range: -2.8825
Max Act: 2.7871. Min Act: -0.1700
Data Index: 441726 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8825. Min Range: -2.8825
Max Act: 2.7871. Min Act: -0.1700
Data Index: 870954 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8825. Min Range: -2.8825
Max Act: 2.7871. Min Act: -0.1700
Data Index: 4635169 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8825. Min Range: -2.8825
Max Act: 2.6913. Min Act: -0.1700
Data Index: 8649040 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8825. Min Range: -2.8825
Max Act: 2.6593. Min Act: -0.1700
Data Index: 4111196 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8825. Min Range: -2.8825
Max Act: 2.6593. Min Act: -0.1700
Data Index: 471534 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8825. Min Range: -2.8825
Max Act: 2.6593. Min Act: -0.1700
Data Index: 6421921 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8825. Min Range: -2.8825
Max Act: 2.6593. Min Act: -0.1700
Data Index: 6395808 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8825. Min Range: -2.8825
Max Act: 2.6593. Min Act: -0.1700
Data Index: 1782683 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8825. Min Range: -2.8825
Max Act: 2.6593. Min Act: -0.1700
Data Index: 5298982 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8825. Min Range: -2.8825
Max Act: 2.6593. Min Act: -0.1700
Data Index: 8470280 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19