Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2054 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0061. Min Range: -4.0061
Max Act: 4.0061. Min Act: -0.1700
Data Index: 2891095 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0061. Min Range: -4.0061
Max Act: 4.0061. Min Act: -0.1700
Data Index: 533014 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0061. Min Range: -4.0061
Max Act: 3.9748. Min Act: -0.1700
Data Index: 8186351 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0061. Min Range: -4.0061
Max Act: 3.9748. Min Act: -0.1700
Data Index: 1923282 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0061. Min Range: -4.0061
Max Act: 3.9748. Min Act: -0.1700
Data Index: 5349806 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0061. Min Range: -4.0061
Max Act: 3.8811. Min Act: -0.1700
Data Index: 5788898 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0061. Min Range: -4.0061
Max Act: 3.8498. Min Act: -0.1700
Data Index: 6704068 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0061. Min Range: -4.0061
Max Act: 3.7560. Min Act: -0.1700
Data Index: 2958344 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0061. Min Range: -4.0061
Max Act: 3.7247. Min Act: -0.1700
Data Index: 1931793 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0061. Min Range: -4.0061
Max Act: 3.7247. Min Act: -0.1700
Data Index: 1245115 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0061. Min Range: -4.0061
Max Act: 3.6934. Min Act: -0.1700
Data Index: 6723779 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0061. Min Range: -4.0061
Max Act: 3.6934. Min Act: -0.1700
Data Index: 6552975 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0061. Min Range: -4.0061
Max Act: 3.6934. Min Act: -0.1700
Data Index: 5811110 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0061. Min Range: -4.0061
Max Act: 3.6934. Min Act: -0.1700
Data Index: 755034 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0061. Min Range: -4.0061
Max Act: 3.6934. Min Act: -0.1700
Data Index: 3510689 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0061. Min Range: -4.0061
Max Act: 3.6934. Min Act: -0.1700
Data Index: 3011417 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0061. Min Range: -4.0061
Max Act: 3.6621. Min Act: -0.1700
Data Index: 1393076 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0061. Min Range: -4.0061
Max Act: 3.6934. Min Act: -0.1700
Data Index: 2690338 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0061. Min Range: -4.0061
Max Act: 3.6934. Min Act: -0.1700
Data Index: 2653317 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0061. Min Range: -4.0061
Max Act: 3.6934. Min Act: -0.1700
Data Index: 924174 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19