Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3730 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5072. Min Range: -3.5072
Max Act: 3.5072. Min Act: -0.1700
Data Index: 142705 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5072. Min Range: -3.5072
Max Act: 3.5072. Min Act: -0.1700
Data Index: 8275504 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5072. Min Range: -3.5072
Max Act: 3.5072. Min Act: -0.1700
Data Index: 8142634 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5072. Min Range: -3.5072
Max Act: 3.4131. Min Act: -0.1700
Data Index: 4956184 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5072. Min Range: -3.5072
Max Act: 3.4131. Min Act: -0.1700
Data Index: 208443 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5072. Min Range: -3.5072
Max Act: 3.3818. Min Act: -0.1700
Data Index: 215316 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5072. Min Range: -3.5072
Max Act: 3.4131. Min Act: -0.1700
Data Index: 4580515 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5072. Min Range: -3.5072
Max Act: 3.4131. Min Act: -0.1700
Data Index: 7911488 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5072. Min Range: -3.5072
Max Act: 3.4131. Min Act: -0.1700
Data Index: 7308061 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5072. Min Range: -3.5072
Max Act: 3.4131. Min Act: -0.1700
Data Index: 7791461 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5072. Min Range: -3.5072
Max Act: 3.3818. Min Act: -0.1700
Data Index: 5621203 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5072. Min Range: -3.5072
Max Act: 3.3818. Min Act: -0.1700
Data Index: 8450021 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5072. Min Range: -3.5072
Max Act: 3.3504. Min Act: -0.1700
Data Index: 4200963 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5072. Min Range: -3.5072
Max Act: 3.3818. Min Act: -0.1700
Data Index: 8109473 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5072. Min Range: -3.5072
Max Act: 3.3818. Min Act: -0.1700
Data Index: 7242340 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5072. Min Range: -3.5072
Max Act: 3.3504. Min Act: -0.1700
Data Index: 462694 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5072. Min Range: -3.5072
Max Act: 3.3818. Min Act: -0.1700
Data Index: 236573 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5072. Min Range: -3.5072
Max Act: 3.3504. Min Act: -0.1700
Data Index: 5341007 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5072. Min Range: -3.5072
Max Act: 3.3504. Min Act: -0.1700
Data Index: 2635803 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5072. Min Range: -3.5072
Max Act: 3.3818. Min Act: -0.1700
Data Index: 53601 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19