Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4136 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9747. Min Range: -6.9747
Max Act: 6.9747. Min Act: -0.1700
Data Index: 433826 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9747. Min Range: -6.9747
Max Act: 6.9435. Min Act: -0.1700
Data Index: 5755773 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9747. Min Range: -6.9747
Max Act: 6.9435. Min Act: -0.1700
Data Index: 4572845 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9747. Min Range: -6.9747
Max Act: 6.8810. Min Act: -0.1700
Data Index: 3790897 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9747. Min Range: -6.9747
Max Act: 6.9122. Min Act: -0.1700
Data Index: 1694335 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9747. Min Range: -6.9747
Max Act: 6.9122. Min Act: -0.1700
Data Index: 5013855 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9747. Min Range: -6.9747
Max Act: 6.9122. Min Act: -0.1700
Data Index: 7949683 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9747. Min Range: -6.9747
Max Act: 6.8810. Min Act: -0.1700
Data Index: 8152819 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9747. Min Range: -6.9747
Max Act: 6.8810. Min Act: -0.1700
Data Index: 6101644 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9747. Min Range: -6.9747
Max Act: 6.8810. Min Act: -0.1700
Data Index: 8618280 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9747. Min Range: -6.9747
Max Act: 6.8810. Min Act: -0.1700
Data Index: 7593480 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9747. Min Range: -6.9747
Max Act: 6.8497. Min Act: -0.1700
Data Index: 5662829 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9747. Min Range: -6.9747
Max Act: 6.8497. Min Act: -0.1700
Data Index: 1156943 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9747. Min Range: -6.9747
Max Act: 6.8497. Min Act: -0.1700
Data Index: 8587647 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9747. Min Range: -6.9747
Max Act: 6.8497. Min Act: -0.1700
Data Index: 5345163 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9747. Min Range: -6.9747
Max Act: 6.8497. Min Act: -0.1700
Data Index: 1872464 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9747. Min Range: -6.9747
Max Act: 6.8185. Min Act: -0.1700
Data Index: 7212430 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9747. Min Range: -6.9747
Max Act: 6.8810. Min Act: -0.1700
Data Index: 2116918 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9747. Min Range: -6.9747
Max Act: 6.8497. Min Act: -0.1700
Data Index: 3643911 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9747. Min Range: -6.9747
Max Act: 6.7872. Min Act: -0.1700
Data Index: 5392750 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19