Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3692 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2827. Min Range: -5.2827
Max Act: 5.2827. Min Act: -0.1700
Data Index: 8777771 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2827. Min Range: -5.2827
Max Act: 5.2827. Min Act: -0.1700
Data Index: 1644136 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2827. Min Range: -5.2827
Max Act: 5.0639. Min Act: -0.1700
Data Index: 8755086 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2827. Min Range: -5.2827
Max Act: 5.0639. Min Act: -0.1700
Data Index: 3264130 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2827. Min Range: -5.2827
Max Act: 5.0639. Min Act: -0.1700
Data Index: 6605916 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2827. Min Range: -5.2827
Max Act: 5.0327. Min Act: -0.1700
Data Index: 6589528 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2827. Min Range: -5.2827
Max Act: 5.0014. Min Act: -0.1700
Data Index: 7995960 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2827. Min Range: -5.2827
Max Act: 5.0014. Min Act: -0.1700
Data Index: 5673398 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2827. Min Range: -5.2827
Max Act: 4.9702. Min Act: -0.1700
Data Index: 8148254 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2827. Min Range: -5.2827
Max Act: 4.9389. Min Act: -0.1700
Data Index: 4107067 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2827. Min Range: -5.2827
Max Act: 4.9389. Min Act: -0.1700
Data Index: 3088613 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2827. Min Range: -5.2827
Max Act: 4.9389. Min Act: -0.1700
Data Index: 6448859 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2827. Min Range: -5.2827
Max Act: 4.9077. Min Act: -0.1700
Data Index: 6120084 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2827. Min Range: -5.2827
Max Act: 4.9077. Min Act: -0.1700
Data Index: 113218 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2827. Min Range: -5.2827
Max Act: 4.9077. Min Act: -0.1700
Data Index: 5959555 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2827. Min Range: -5.2827
Max Act: 4.9077. Min Act: -0.1700
Data Index: 4577804 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2827. Min Range: -5.2827
Max Act: 4.8764. Min Act: -0.1700
Data Index: 2575032 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2827. Min Range: -5.2827
Max Act: 4.8764. Min Act: -0.1700
Data Index: 8236169 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2827. Min Range: -5.2827
Max Act: 4.8764. Min Act: -0.1700
Data Index: 8207082 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2827. Min Range: -5.2827
Max Act: 4.8764. Min Act: -0.1700
Data Index: 7139197 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19