Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3167 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.9618. Min Act: -0.1700
Data Index: 845826 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.9618. Min Act: -0.1700
Data Index: 1575099 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.9618. Min Act: -0.1694
Data Index: 328107 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.9618. Min Act: -0.1700
Data Index: 1211049 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.9618. Min Act: -0.1700
Data Index: 316045 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.9618. Min Act: -0.1700
Data Index: 1201841 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.9618. Min Act: -0.1700
Data Index: 1489417 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.9618. Min Act: -0.1700
Data Index: 250880 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.9618. Min Act: -0.1700
Data Index: 1394768 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.9618. Min Act: -0.1700
Data Index: 403369 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.9618. Min Act: -0.1700
Data Index: 1837271 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.9618. Min Act: -0.1700
Data Index: 1747609 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.9618. Min Act: -0.1700
Data Index: 2155146 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.9618. Min Act: -0.1700
Data Index: 2090870 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.9618. Min Act: -0.1700
Data Index: 1375957 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.9618. Min Act: -0.1700
Data Index: 508299 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.9618. Min Act: -0.1700
Data Index: 1961680 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.9618. Min Act: -0.1700
Data Index: 1958741 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.9618. Min Act: -0.1700
Data Index: 1852530 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9618. Min Range: -3.9618
Max Act: 3.9618. Min Act: -0.1700
Data Index: 53649 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19