Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1174 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0703. Min Range: -5.0703
Max Act: 5.0703. Min Act: -0.1700
Data Index: 1951876 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0703. Min Range: -5.0703
Max Act: 5.0703. Min Act: -0.1700
Data Index: 3725180 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0703. Min Range: -5.0703
Max Act: 5.0391. Min Act: -0.1700
Data Index: 3510013 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0703. Min Range: -5.0703
Max Act: 5.0391. Min Act: -0.1700
Data Index: 509604 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0703. Min Range: -5.0703
Max Act: 5.0391. Min Act: -0.1700
Data Index: 2837270 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.9766. Min Act: -0.1700
Data Index: 3353009 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.9766. Min Act: -0.1700
Data Index: 7177232 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0703. Min Range: -5.0703
Max Act: 5.0078. Min Act: -0.1700
Data Index: 1913610 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0703. Min Range: -5.0703
Max Act: 5.0078. Min Act: -0.1700
Data Index: 1899041 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0703. Min Range: -5.0703
Max Act: 5.0078. Min Act: -0.1700
Data Index: 6303252 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0703. Min Range: -5.0703
Max Act: 5.0078. Min Act: -0.1700
Data Index: 5224465 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.9766. Min Act: -0.1700
Data Index: 4898749 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0703. Min Range: -5.0703
Max Act: 5.0078. Min Act: -0.1700
Data Index: 2749500 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0703. Min Range: -5.0703
Max Act: 5.0078. Min Act: -0.1700
Data Index: 1318385 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0703. Min Range: -5.0703
Max Act: 5.0078. Min Act: -0.1700
Data Index: 1171128 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0703. Min Range: -5.0703
Max Act: 5.0078. Min Act: -0.1700
Data Index: 8594379 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.9766. Min Act: -0.1700
Data Index: 4650923 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.9766. Min Act: -0.1700
Data Index: 1098251 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.9453. Min Act: -0.1700
Data Index: 940409 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.9766. Min Act: -0.1700
Data Index: 3753548 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19