Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2886 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3484. Min Range: -3.3484
Max Act: 3.3484. Min Act: -0.1700
Data Index: 5979531 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3484. Min Range: -3.3484
Max Act: 3.3170. Min Act: -0.1700
Data Index: 932438 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3484. Min Range: -3.3484
Max Act: 3.1599. Min Act: -0.1700
Data Index: 1458178 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3484. Min Range: -3.3484
Max Act: 3.1441. Min Act: -0.1700
Data Index: 337476 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3484. Min Range: -3.3484
Max Act: 3.1441. Min Act: -0.1700
Data Index: 4211156 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3484. Min Range: -3.3484
Max Act: 3.1284. Min Act: -0.1700
Data Index: 7000793 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3484. Min Range: -3.3484
Max Act: 3.1126. Min Act: -0.1700
Data Index: 4352490 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3484. Min Range: -3.3484
Max Act: 3.1126. Min Act: -0.1700
Data Index: 1841696 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3484. Min Range: -3.3484
Max Act: 3.0811. Min Act: -0.1700
Data Index: 7252524 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3484. Min Range: -3.3484
Max Act: 3.0653. Min Act: -0.1700
Data Index: 2537151 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3484. Min Range: -3.3484
Max Act: 3.0495. Min Act: -0.1700
Data Index: 6453381 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3484. Min Range: -3.3484
Max Act: 3.0495. Min Act: -0.1700
Data Index: 7163593 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3484. Min Range: -3.3484
Max Act: 3.0180. Min Act: -0.1700
Data Index: 5368523 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3484. Min Range: -3.3484
Max Act: 3.0338. Min Act: -0.1700
Data Index: 4039817 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3484. Min Range: -3.3484
Max Act: 3.0338. Min Act: -0.1700
Data Index: 7225710 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3484. Min Range: -3.3484
Max Act: 3.0180. Min Act: -0.1700
Data Index: 6440510 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3484. Min Range: -3.3484
Max Act: 3.0180. Min Act: -0.1700
Data Index: 5044213 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3484. Min Range: -3.3484
Max Act: 3.0180. Min Act: -0.1700
Data Index: 8241999 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3484. Min Range: -3.3484
Max Act: 3.0022. Min Act: -0.1700
Data Index: 1698728 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3484. Min Range: -3.3484
Max Act: 3.0180. Min Act: -0.1700
Data Index: 4719760 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19