Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2213 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.9004. Min Act: -0.1700
Data Index: 2918523 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.9004. Min Act: -0.1700
Data Index: 1190005 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.9004. Min Act: -0.1700
Data Index: 3066906 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.9004. Min Act: -0.1700
Data Index: 4972936 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.9004. Min Act: -0.1700
Data Index: 5417356 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.9004. Min Act: -0.1700
Data Index: 5674010 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.9004. Min Act: -0.1700
Data Index: 5813831 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.8846. Min Act: -0.1700
Data Index: 4896224 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.8846. Min Act: -0.1700
Data Index: 1814178 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.8846. Min Act: -0.1700
Data Index: 4737057 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.8687. Min Act: -0.1700
Data Index: 1100040 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.8687. Min Act: -0.1700
Data Index: 7456874 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.8528. Min Act: -0.1700
Data Index: 5413103 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.8528. Min Act: -0.1700
Data Index: 2034462 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.8528. Min Act: -0.1700
Data Index: 5308356 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.8528. Min Act: -0.1700
Data Index: 3426910 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.8528. Min Act: -0.1700
Data Index: 677905 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.8369. Min Act: -0.1700
Data Index: 2128990 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.8369. Min Act: -0.1700
Data Index: 2193308 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9004. Min Range: -2.9004
Max Act: 2.8369. Min Act: -0.1700
Data Index: 4108605 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19