Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 873 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1762. Min Range: -4.1762
Max Act: 4.1762. Min Act: -0.1700
Data Index: 3371736 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1762. Min Range: -4.1762
Max Act: 4.1137. Min Act: -0.1700
Data Index: 1611367 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1762. Min Range: -4.1762
Max Act: 4.0825. Min Act: -0.1700
Data Index: 3648529 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1762. Min Range: -4.1762
Max Act: 4.0825. Min Act: -0.1700
Data Index: 5896926 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1762. Min Range: -4.1762
Max Act: 4.0825. Min Act: -0.1700
Data Index: 2845702 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1762. Min Range: -4.1762
Max Act: 4.0825. Min Act: -0.1700
Data Index: 547315 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1762. Min Range: -4.1762
Max Act: 4.0825. Min Act: -0.1700
Data Index: 1177961 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1762. Min Range: -4.1762
Max Act: 4.0512. Min Act: -0.1700
Data Index: 6737689 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1762. Min Range: -4.1762
Max Act: 4.0512. Min Act: -0.1700
Data Index: 3382077 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1762. Min Range: -4.1762
Max Act: 4.0512. Min Act: -0.1700
Data Index: 2729839 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1762. Min Range: -4.1762
Max Act: 4.0512. Min Act: -0.1700
Data Index: 5503090 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1762. Min Range: -4.1762
Max Act: 4.0512. Min Act: -0.1700
Data Index: 6210325 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1762. Min Range: -4.1762
Max Act: 4.0512. Min Act: -0.1700
Data Index: 2065434 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1762. Min Range: -4.1762
Max Act: 4.0512. Min Act: -0.1700
Data Index: 4736596 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1762. Min Range: -4.1762
Max Act: 4.0512. Min Act: -0.1700
Data Index: 4212741 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1762. Min Range: -4.1762
Max Act: 4.0512. Min Act: -0.1700
Data Index: 723928 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1762. Min Range: -4.1762
Max Act: 4.0512. Min Act: -0.1700
Data Index: 682460 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1762. Min Range: -4.1762
Max Act: 4.0512. Min Act: -0.1700
Data Index: 36276 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1762. Min Range: -4.1762
Max Act: 4.0512. Min Act: -0.1700
Data Index: 3967860 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1762. Min Range: -4.1762
Max Act: 4.0512. Min Act: -0.1700
Data Index: 1475390 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19