Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1243 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9007. Min Range: -2.9007
Max Act: 2.9007. Min Act: -0.1700
Data Index: 1851705 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9007. Min Range: -2.9007
Max Act: 2.8690. Min Act: -0.1700
Data Index: 993584 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9007. Min Range: -2.9007
Max Act: 2.8849. Min Act: -0.1700
Data Index: 6704134 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9007. Min Range: -2.9007
Max Act: 2.8849. Min Act: -0.1700
Data Index: 4045908 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9007. Min Range: -2.9007
Max Act: 2.8690. Min Act: -0.1700
Data Index: 4713089 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9007. Min Range: -2.9007
Max Act: 2.8690. Min Act: -0.1700
Data Index: 1429591 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9007. Min Range: -2.9007
Max Act: 2.8531. Min Act: -0.1700
Data Index: 685361 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9007. Min Range: -2.9007
Max Act: 2.8690. Min Act: -0.1700
Data Index: 2511759 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9007. Min Range: -2.9007
Max Act: 2.8372. Min Act: -0.1700
Data Index: 272114 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9007. Min Range: -2.9007
Max Act: 2.8372. Min Act: -0.1700
Data Index: 849138 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9007. Min Range: -2.9007
Max Act: 2.8372. Min Act: -0.1700
Data Index: 161756 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9007. Min Range: -2.9007
Max Act: 2.8372. Min Act: -0.1700
Data Index: 1013773 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9007. Min Range: -2.9007
Max Act: 2.8372. Min Act: -0.1700
Data Index: 895389 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9007. Min Range: -2.9007
Max Act: 2.8372. Min Act: -0.1700
Data Index: 926188 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9007. Min Range: -2.9007
Max Act: 2.8372. Min Act: -0.1700
Data Index: 346060 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9007. Min Range: -2.9007
Max Act: 2.8372. Min Act: -0.1700
Data Index: 660311 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9007. Min Range: -2.9007
Max Act: 2.8372. Min Act: -0.1700
Data Index: 1016965 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9007. Min Range: -2.9007
Max Act: 2.8531. Min Act: -0.1700
Data Index: 715569 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9007. Min Range: -2.9007
Max Act: 2.8372. Min Act: -0.1700
Data Index: 308556 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9007. Min Range: -2.9007
Max Act: 2.8372. Min Act: -0.1700
Data Index: 735935 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19