Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3815 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7808. Min Range: -4.7808
Max Act: 4.7808. Min Act: -0.1700
Data Index: 4493033 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7808. Min Range: -4.7808
Max Act: 4.7183. Min Act: -0.1700
Data Index: 6563013 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7808. Min Range: -4.7808
Max Act: 4.7183. Min Act: -0.1700
Data Index: 1131645 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7808. Min Range: -4.7808
Max Act: 4.7183. Min Act: -0.1700
Data Index: 7285515 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7808. Min Range: -4.7808
Max Act: 4.7183. Min Act: -0.1700
Data Index: 7106912 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7808. Min Range: -4.7808
Max Act: 4.7183. Min Act: -0.1700
Data Index: 1538264 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7808. Min Range: -4.7808
Max Act: 4.7183. Min Act: -0.1700
Data Index: 6675273 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7808. Min Range: -4.7808
Max Act: 4.7183. Min Act: -0.1700
Data Index: 6453185 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7808. Min Range: -4.7808
Max Act: 4.6870. Min Act: -0.1700
Data Index: 515251 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7808. Min Range: -4.7808
Max Act: 4.6558. Min Act: -0.1700
Data Index: 8001912 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7808. Min Range: -4.7808
Max Act: 4.6558. Min Act: -0.1700
Data Index: 2376421 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7808. Min Range: -4.7808
Max Act: 4.6870. Min Act: -0.1700
Data Index: 7568683 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7808. Min Range: -4.7808
Max Act: 4.6870. Min Act: -0.1700
Data Index: 6726728 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7808. Min Range: -4.7808
Max Act: 4.6870. Min Act: -0.1700
Data Index: 5611231 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7808. Min Range: -4.7808
Max Act: 4.6558. Min Act: -0.1700
Data Index: 6093522 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7808. Min Range: -4.7808
Max Act: 4.6558. Min Act: -0.1700
Data Index: 704034 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7808. Min Range: -4.7808
Max Act: 4.6558. Min Act: -0.1700
Data Index: 4668832 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7808. Min Range: -4.7808
Max Act: 4.6558. Min Act: -0.1700
Data Index: 3622613 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7808. Min Range: -4.7808
Max Act: 4.6245. Min Act: -0.1700
Data Index: 1251656 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7808. Min Range: -4.7808
Max Act: 4.6558. Min Act: -0.1700
Data Index: 7957770 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19