Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1939 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3571. Min Range: -6.3571
Max Act: 6.3571. Min Act: -0.1700
Data Index: 4362051 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3571. Min Range: -6.3571
Max Act: 6.2634. Min Act: -0.1700
Data Index: 7848775 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3571. Min Range: -6.3571
Max Act: 6.2321. Min Act: -0.1700
Data Index: 5924569 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3571. Min Range: -6.3571
Max Act: 6.2009. Min Act: -0.1700
Data Index: 1378131 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3571. Min Range: -6.3571
Max Act: 6.2009. Min Act: -0.1700
Data Index: 4562565 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3571. Min Range: -6.3571
Max Act: 6.1696. Min Act: -0.1700
Data Index: 7365576 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3571. Min Range: -6.3571
Max Act: 6.1384. Min Act: -0.1700
Data Index: 6781340 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3571. Min Range: -6.3571
Max Act: 6.1071. Min Act: -0.1700
Data Index: 1266208 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3571. Min Range: -6.3571
Max Act: 6.1071. Min Act: -0.1700
Data Index: 426164 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3571. Min Range: -6.3571
Max Act: 6.0446. Min Act: -0.1700
Data Index: 8334140 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3571. Min Range: -6.3571
Max Act: 6.0134. Min Act: -0.1700
Data Index: 1778694 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3571. Min Range: -6.3571
Max Act: 6.0134. Min Act: -0.1700
Data Index: 2771366 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3571. Min Range: -6.3571
Max Act: 6.0134. Min Act: -0.1700
Data Index: 7106992 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3571. Min Range: -6.3571
Max Act: 6.0134. Min Act: -0.1700
Data Index: 782500 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3571. Min Range: -6.3571
Max Act: 6.0134. Min Act: -0.1700
Data Index: 7102023 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3571. Min Range: -6.3571
Max Act: 5.9821. Min Act: -0.1700
Data Index: 7500346 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3571. Min Range: -6.3571
Max Act: 6.0134. Min Act: -0.1700
Data Index: 6807253 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3571. Min Range: -6.3571
Max Act: 5.9821. Min Act: -0.1700
Data Index: 5130120 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3571. Min Range: -6.3571
Max Act: 5.9509. Min Act: -0.1700
Data Index: 1302571 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3571. Min Range: -6.3571
Max Act: 5.9509. Min Act: -0.1700
Data Index: 5608175 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19