Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3272 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6331. Min Range: -3.6331
Max Act: 3.6331. Min Act: -0.1700
Data Index: 2376428 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6331. Min Range: -3.6331
Max Act: 3.6331. Min Act: -0.1700
Data Index: 7513764 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6331. Min Range: -3.6331
Max Act: 3.6331. Min Act: -0.1700
Data Index: 6110130 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6331. Min Range: -3.6331
Max Act: 3.6331. Min Act: -0.1700
Data Index: 5856221 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6331. Min Range: -3.6331
Max Act: 3.6331. Min Act: -0.1700
Data Index: 3938805 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6331. Min Range: -3.6331
Max Act: 3.6018. Min Act: -0.1700
Data Index: 1810300 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6331. Min Range: -3.6331
Max Act: 3.6018. Min Act: -0.1700
Data Index: 3856681 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6331. Min Range: -3.6331
Max Act: 3.6018. Min Act: -0.1700
Data Index: 2167431 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6331. Min Range: -3.6331
Max Act: 3.6018. Min Act: -0.1700
Data Index: 6007708 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6331. Min Range: -3.6331
Max Act: 3.6018. Min Act: -0.1700
Data Index: 8490169 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6331. Min Range: -3.6331
Max Act: 3.5705. Min Act: -0.1700
Data Index: 7750764 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6331. Min Range: -3.6331
Max Act: 3.6018. Min Act: -0.1700
Data Index: 7221941 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6331. Min Range: -3.6331
Max Act: 3.6018. Min Act: -0.1700
Data Index: 6373811 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6331. Min Range: -3.6331
Max Act: 3.6018. Min Act: -0.1700
Data Index: 4654799 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6331. Min Range: -3.6331
Max Act: 3.5705. Min Act: -0.1700
Data Index: 2994570 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6331. Min Range: -3.6331
Max Act: 3.5705. Min Act: -0.1700
Data Index: 5961508 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6331. Min Range: -3.6331
Max Act: 3.5705. Min Act: -0.1700
Data Index: 3167155 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6331. Min Range: -3.6331
Max Act: 3.5705. Min Act: -0.1700
Data Index: 1978186 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6331. Min Range: -3.6331
Max Act: 3.5705. Min Act: -0.1700
Data Index: 2062105 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6331. Min Range: -3.6331
Max Act: 3.6018. Min Act: -0.1700
Data Index: 3852619 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19