Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2202 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1926. Min Range: -4.1926
Max Act: 4.1926. Min Act: -0.1700
Data Index: 7922533 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1926. Min Range: -4.1926
Max Act: 4.1613. Min Act: -0.1700
Data Index: 6009045 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1926. Min Range: -4.1926
Max Act: 4.1301. Min Act: -0.1700
Data Index: 3480697 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1926. Min Range: -4.1926
Max Act: 4.0675. Min Act: -0.1700
Data Index: 1478599 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1926. Min Range: -4.1926
Max Act: 4.0988. Min Act: -0.1700
Data Index: 1198660 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1926. Min Range: -4.1926
Max Act: 4.0675. Min Act: -0.1700
Data Index: 5544023 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1926. Min Range: -4.1926
Max Act: 4.0675. Min Act: -0.1700
Data Index: 3673666 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1926. Min Range: -4.1926
Max Act: 4.0675. Min Act: -0.1700
Data Index: 5241965 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1926. Min Range: -4.1926
Max Act: 4.0675. Min Act: -0.1700
Data Index: 2627989 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1926. Min Range: -4.1926
Max Act: 4.0675. Min Act: -0.1700
Data Index: 6853898 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1926. Min Range: -4.1926
Max Act: 4.0675. Min Act: -0.1700
Data Index: 6164220 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1926. Min Range: -4.1926
Max Act: 4.0363. Min Act: -0.1700
Data Index: 1587163 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1926. Min Range: -4.1926
Max Act: 4.0363. Min Act: -0.1700
Data Index: 826069 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1926. Min Range: -4.1926
Max Act: 4.0363. Min Act: -0.1700
Data Index: 3986449 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1926. Min Range: -4.1926
Max Act: 4.0363. Min Act: -0.1700
Data Index: 3344801 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1926. Min Range: -4.1926
Max Act: 4.0363. Min Act: -0.1700
Data Index: 1793141 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1926. Min Range: -4.1926
Max Act: 4.0363. Min Act: -0.1700
Data Index: 5858439 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1926. Min Range: -4.1926
Max Act: 4.0363. Min Act: -0.1700
Data Index: 212148 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1926. Min Range: -4.1926
Max Act: 4.0363. Min Act: -0.1700
Data Index: 4048973 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1926. Min Range: -4.1926
Max Act: 4.0363. Min Act: -0.1700
Data Index: 4265388 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19