Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4042 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8594. Min Range: -1.8594
Max Act: 1.8594. Min Act: -0.1700
Data Index: 7093101 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8594. Min Range: -1.8594
Max Act: 1.8079. Min Act: -0.1700
Data Index: 8407887 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8594. Min Range: -1.8594
Max Act: 1.8251. Min Act: -0.1700
Data Index: 4835906 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8594. Min Range: -1.8594
Max Act: 1.8251. Min Act: -0.1700
Data Index: 5832927 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8594. Min Range: -1.8594
Max Act: 1.7907. Min Act: -0.1700
Data Index: 3112698 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8594. Min Range: -1.8594
Max Act: 1.7907. Min Act: -0.1700
Data Index: 351359 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8594. Min Range: -1.8594
Max Act: 1.7907. Min Act: -0.1700
Data Index: 1878146 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8594. Min Range: -1.8594
Max Act: 1.8079. Min Act: -0.1700
Data Index: 2490514 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8594. Min Range: -1.8594
Max Act: 1.7907. Min Act: -0.1700
Data Index: 7103704 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8594. Min Range: -1.8594
Max Act: 1.7907. Min Act: -0.1700
Data Index: 5642931 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8594. Min Range: -1.8594
Max Act: 1.7907. Min Act: -0.1700
Data Index: 5629320 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8594. Min Range: -1.8594
Max Act: 1.7907. Min Act: -0.1700
Data Index: 5496110 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8594. Min Range: -1.8594
Max Act: 1.7907. Min Act: -0.1700
Data Index: 5359223 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8594. Min Range: -1.8594
Max Act: 1.7907. Min Act: -0.1700
Data Index: 5119442 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8594. Min Range: -1.8594
Max Act: 1.7907. Min Act: -0.1700
Data Index: 3152807 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8594. Min Range: -1.8594
Max Act: 1.7907. Min Act: -0.1700
Data Index: 6768313 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8594. Min Range: -1.8594
Max Act: 1.7907. Min Act: -0.1700
Data Index: 1857494 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8594. Min Range: -1.8594
Max Act: 1.7907. Min Act: -0.1700
Data Index: 1831830 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8594. Min Range: -1.8594
Max Act: 1.7907. Min Act: -0.1700
Data Index: 2589095 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8594. Min Range: -1.8594
Max Act: 1.7907. Min Act: -0.1700
Data Index: 2830764 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19