Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5067 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.8585. Min Range: -1.8585
Max Act: 1.8585. Min Act: -0.1700
Data Index: 679304 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8585. Min Range: -1.8585
Max Act: 1.8413. Min Act: -0.1700
Data Index: 2442727 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8585. Min Range: -1.8585
Max Act: 1.8413. Min Act: -0.1700
Data Index: 6267662 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8585. Min Range: -1.8585
Max Act: 1.8413. Min Act: -0.1700
Data Index: 4844765 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8585. Min Range: -1.8585
Max Act: 1.8242. Min Act: -0.1700
Data Index: 6601957 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8585. Min Range: -1.8585
Max Act: 1.8070. Min Act: -0.1700
Data Index: 5297744 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8585. Min Range: -1.8585
Max Act: 1.8070. Min Act: -0.1700
Data Index: 330398 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8585. Min Range: -1.8585
Max Act: 1.8070. Min Act: -0.1700
Data Index: 4275566 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8585. Min Range: -1.8585
Max Act: 1.8070. Min Act: -0.1700
Data Index: 8646309 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8585. Min Range: -1.8585
Max Act: 1.8070. Min Act: -0.1700
Data Index: 4090991 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8585. Min Range: -1.8585
Max Act: 1.8070. Min Act: -0.1700
Data Index: 1838295 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8585. Min Range: -1.8585
Max Act: 1.8070. Min Act: -0.1700
Data Index: 5893127 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8585. Min Range: -1.8585
Max Act: 1.8242. Min Act: -0.1700
Data Index: 2402606 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8585. Min Range: -1.8585
Max Act: 1.8070. Min Act: -0.1700
Data Index: 2191352 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8585. Min Range: -1.8585
Max Act: 1.7898. Min Act: -0.1700
Data Index: 4471673 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8585. Min Range: -1.8585
Max Act: 1.7898. Min Act: -0.1700
Data Index: 933846 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8585. Min Range: -1.8585
Max Act: 1.7898. Min Act: -0.1700
Data Index: 8534683 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8585. Min Range: -1.8585
Max Act: 1.7898. Min Act: -0.1700
Data Index: 2259907 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8585. Min Range: -1.8585
Max Act: 1.7898. Min Act: -0.1700
Data Index: 5230929 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8585. Min Range: -1.8585
Max Act: 1.7898. Min Act: -0.1700
Data Index: 5811213 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19