Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2919 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8501. Min Range: -3.8501
Max Act: 3.8501. Min Act: -0.1700
Data Index: 1612975 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8501. Min Range: -3.8501
Max Act: 3.8188. Min Act: -0.1700
Data Index: 7850599 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8501. Min Range: -3.8501
Max Act: 3.8188. Min Act: -0.1700
Data Index: 7612248 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8501. Min Range: -3.8501
Max Act: 3.8188. Min Act: -0.1700
Data Index: 5464655 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8501. Min Range: -3.8501
Max Act: 3.8188. Min Act: -0.1700
Data Index: 4968343 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8501. Min Range: -3.8501
Max Act: 3.8188. Min Act: -0.1700
Data Index: 5430683 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8501. Min Range: -3.8501
Max Act: 3.7876. Min Act: -0.1700
Data Index: 3286204 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8501. Min Range: -3.8501
Max Act: 3.7563. Min Act: -0.1700
Data Index: 7766271 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8501. Min Range: -3.8501
Max Act: 3.7563. Min Act: -0.1700
Data Index: 5972377 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8501. Min Range: -3.8501
Max Act: 3.7876. Min Act: -0.1700
Data Index: 305941 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8501. Min Range: -3.8501
Max Act: 3.7876. Min Act: -0.1700
Data Index: 7490985 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8501. Min Range: -3.8501
Max Act: 3.7563. Min Act: -0.1700
Data Index: 1719711 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8501. Min Range: -3.8501
Max Act: 3.7563. Min Act: -0.1700
Data Index: 4335333 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8501. Min Range: -3.8501
Max Act: 3.7563. Min Act: -0.1700
Data Index: 8237851 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8501. Min Range: -3.8501
Max Act: 3.7876. Min Act: -0.1700
Data Index: 4134926 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8501. Min Range: -3.8501
Max Act: 3.7563. Min Act: -0.1700
Data Index: 2597634 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8501. Min Range: -3.8501
Max Act: 3.7876. Min Act: -0.1700
Data Index: 3799374 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8501. Min Range: -3.8501
Max Act: 3.7876. Min Act: -0.1700
Data Index: 2164326 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8501. Min Range: -3.8501
Max Act: 3.7563. Min Act: -0.1700
Data Index: 7187124 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8501. Min Range: -3.8501
Max Act: 3.7250. Min Act: -0.1700
Data Index: 7337536 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19