Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4603 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2844. Min Range: -4.2844
Max Act: 4.2844. Min Act: -0.1700
Data Index: 2047220 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2844. Min Range: -4.2844
Max Act: 4.2531. Min Act: -0.1700
Data Index: 950524 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2844. Min Range: -4.2844
Max Act: 4.2531. Min Act: -0.1700
Data Index: 6652244 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2844. Min Range: -4.2844
Max Act: 4.2531. Min Act: -0.1700
Data Index: 2102962 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2844. Min Range: -4.2844
Max Act: 4.2531. Min Act: -0.1700
Data Index: 4626458 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2844. Min Range: -4.2844
Max Act: 4.2531. Min Act: -0.1700
Data Index: 4032148 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2844. Min Range: -4.2844
Max Act: 4.2219. Min Act: -0.1700
Data Index: 964657 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2844. Min Range: -4.2844
Max Act: 4.2219. Min Act: -0.1700
Data Index: 6143336 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2844. Min Range: -4.2844
Max Act: 4.2219. Min Act: -0.1700
Data Index: 5643790 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2844. Min Range: -4.2844
Max Act: 4.2219. Min Act: -0.1700
Data Index: 7027788 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2844. Min Range: -4.2844
Max Act: 4.1906. Min Act: -0.1700
Data Index: 2590385 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2844. Min Range: -4.2844
Max Act: 4.1906. Min Act: -0.1700
Data Index: 5510928 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2844. Min Range: -4.2844
Max Act: 4.2219. Min Act: -0.1700
Data Index: 1956212 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2844. Min Range: -4.2844
Max Act: 4.2219. Min Act: -0.1700
Data Index: 3224953 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2844. Min Range: -4.2844
Max Act: 4.1906. Min Act: -0.1700
Data Index: 7881866 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2844. Min Range: -4.2844
Max Act: 4.1594. Min Act: -0.1700
Data Index: 8498060 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2844. Min Range: -4.2844
Max Act: 4.1906. Min Act: -0.1700
Data Index: 5794537 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2844. Min Range: -4.2844
Max Act: 4.1594. Min Act: -0.1700
Data Index: 2242720 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2844. Min Range: -4.2844
Max Act: 4.1594. Min Act: -0.1700
Data Index: 8490791 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2844. Min Range: -4.2844
Max Act: 4.1281. Min Act: -0.1700
Data Index: 5825367 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19