Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2165 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.7073. Min Range: -7.7073
Max Act: 7.7073. Min Act: -0.1700
Data Index: 356207 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7073. Min Range: -7.7073
Max Act: 7.6760. Min Act: -0.1700
Data Index: 8748360 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7073. Min Range: -7.7073
Max Act: 7.5823. Min Act: -0.1700
Data Index: 218169 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7073. Min Range: -7.7073
Max Act: 7.4885. Min Act: -0.1700
Data Index: 1483431 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7073. Min Range: -7.7073
Max Act: 7.3635. Min Act: -0.1700
Data Index: 6153133 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7073. Min Range: -7.7073
Max Act: 7.3635. Min Act: -0.1700
Data Index: 3795742 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7073. Min Range: -7.7073
Max Act: 7.3010. Min Act: -0.1700
Data Index: 171876 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7073. Min Range: -7.7073
Max Act: 7.2073. Min Act: -0.1700
Data Index: 3830086 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7073. Min Range: -7.7073
Max Act: 7.1760. Min Act: -0.1700
Data Index: 3986641 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7073. Min Range: -7.7073
Max Act: 7.2073. Min Act: -0.1700
Data Index: 1081849 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7073. Min Range: -7.7073
Max Act: 7.1135. Min Act: -0.1700
Data Index: 3302710 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7073. Min Range: -7.7073
Max Act: 7.1448. Min Act: -0.1700
Data Index: 1029959 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7073. Min Range: -7.7073
Max Act: 7.1135. Min Act: -0.1700
Data Index: 291636 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7073. Min Range: -7.7073
Max Act: 7.0823. Min Act: -0.1700
Data Index: 2151528 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7073. Min Range: -7.7073
Max Act: 7.0823. Min Act: -0.1700
Data Index: 6042028 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7073. Min Range: -7.7073
Max Act: 7.0510. Min Act: -0.1700
Data Index: 765260 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7073. Min Range: -7.7073
Max Act: 7.1135. Min Act: -0.1700
Data Index: 1037673 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7073. Min Range: -7.7073
Max Act: 7.0510. Min Act: -0.1700
Data Index: 163465 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7073. Min Range: -7.7073
Max Act: 7.0198. Min Act: -0.1700
Data Index: 4794111 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7073. Min Range: -7.7073
Max Act: 7.0198. Min Act: -0.1700
Data Index: 674702 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19