Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2168 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.8501. Min Range: -11.8501
Max Act: 11.8501. Min Act: -0.1700
Data Index: 8039939 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.8501. Min Range: -11.8501
Max Act: 11.6001. Min Act: -0.1700
Data Index: 6400192 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.8501. Min Range: -11.8501
Max Act: 11.5376. Min Act: -0.1700
Data Index: 431853 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.8501. Min Range: -11.8501
Max Act: 10.9751. Min Act: -0.1700
Data Index: 1624131 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.8501. Min Range: -11.8501
Max Act: 10.9751. Min Act: -0.1700
Data Index: 4786304 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.8501. Min Range: -11.8501
Max Act: 10.8501. Min Act: -0.1700
Data Index: 1858452 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.8501. Min Range: -11.8501
Max Act: 10.8501. Min Act: -0.1700
Data Index: 2361751 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.8501. Min Range: -11.8501
Max Act: 10.7876. Min Act: -0.1700
Data Index: 5880576 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.8501. Min Range: -11.8501
Max Act: 10.7251. Min Act: -0.1700
Data Index: 4809341 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.8501. Min Range: -11.8501
Max Act: 10.7876. Min Act: -0.1700
Data Index: 3085126 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.8501. Min Range: -11.8501
Max Act: 10.7251. Min Act: -0.1700
Data Index: 346869 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.8501. Min Range: -11.8501
Max Act: 10.7251. Min Act: -0.1700
Data Index: 119582 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.8501. Min Range: -11.8501
Max Act: 10.6626. Min Act: -0.1699
Data Index: 2884782 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.8501. Min Range: -11.8501
Max Act: 10.6626. Min Act: -0.1700
Data Index: 39572 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.8501. Min Range: -11.8501
Max Act: 10.6626. Min Act: -0.1700
Data Index: 4185874 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.8501. Min Range: -11.8501
Max Act: 10.6626. Min Act: -0.1700
Data Index: 8371764 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.8501. Min Range: -11.8501
Max Act: 10.6001. Min Act: -0.1700
Data Index: 7206524 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.8501. Min Range: -11.8501
Max Act: 10.4751. Min Act: -0.1700
Data Index: 3955546 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.8501. Min Range: -11.8501
Max Act: 10.5376. Min Act: -0.1700
Data Index: 5153102 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.8501. Min Range: -11.8501
Max Act: 10.6001. Min Act: -0.1700
Data Index: 8575465 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19