Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2997 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1368. Min Range: -5.1368
Max Act: 5.1368. Min Act: -0.1700
Data Index: 4543170 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1368. Min Range: -5.1368
Max Act: 5.1055. Min Act: -0.1700
Data Index: 4735849 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1368. Min Range: -5.1368
Max Act: 5.1055. Min Act: -0.1700
Data Index: 5746420 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1368. Min Range: -5.1368
Max Act: 5.0743. Min Act: -0.1700
Data Index: 4518060 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1368. Min Range: -5.1368
Max Act: 5.0743. Min Act: -0.1700
Data Index: 7772394 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1368. Min Range: -5.1368
Max Act: 5.0743. Min Act: -0.1700
Data Index: 1692386 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1368. Min Range: -5.1368
Max Act: 5.0743. Min Act: -0.1700
Data Index: 8557996 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1368. Min Range: -5.1368
Max Act: 5.0430. Min Act: -0.1700
Data Index: 4518061 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1368. Min Range: -5.1368
Max Act: 5.0118. Min Act: -0.1700
Data Index: 5425256 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1368. Min Range: -5.1368
Max Act: 5.0118. Min Act: -0.1700
Data Index: 6152924 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1368. Min Range: -5.1368
Max Act: 4.9805. Min Act: -0.1700
Data Index: 5945012 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1368. Min Range: -5.1368
Max Act: 4.9805. Min Act: -0.1700
Data Index: 8704400 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1368. Min Range: -5.1368
Max Act: 4.9805. Min Act: -0.1700
Data Index: 4962 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1368. Min Range: -5.1368
Max Act: 4.9493. Min Act: -0.1699
Data Index: 5206348 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1368. Min Range: -5.1368
Max Act: 4.9805. Min Act: -0.1699
Data Index: 5059917 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1368. Min Range: -5.1368
Max Act: 4.9805. Min Act: -0.1700
Data Index: 1654512 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1368. Min Range: -5.1368
Max Act: 4.9493. Min Act: -0.1700
Data Index: 2527652 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1368. Min Range: -5.1368
Max Act: 4.9180. Min Act: -0.1700
Data Index: 117669 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1368. Min Range: -5.1368
Max Act: 4.9493. Min Act: -0.1700
Data Index: 2722754 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1368. Min Range: -5.1368
Max Act: 4.9493. Min Act: -0.1700
Data Index: 3251552 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #19