Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2010 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3834. Min Range: -6.3834
Max Act: 6.3834. Min Act: -0.1700
Data Index: 3199430 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3834. Min Range: -6.3834
Max Act: 6.0709. Min Act: -0.1700
Data Index: 3673161 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3834. Min Range: -6.3834
Max Act: 6.0084. Min Act: -0.1700
Data Index: 418213 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3834. Min Range: -6.3834
Max Act: 5.9772. Min Act: -0.1700
Data Index: 3259898 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3834. Min Range: -6.3834
Max Act: 5.9772. Min Act: -0.1700
Data Index: 1591775 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3834. Min Range: -6.3834
Max Act: 5.9147. Min Act: -0.1700
Data Index: 7395428 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3834. Min Range: -6.3834
Max Act: 5.9147. Min Act: -0.1700
Data Index: 8798543 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3834. Min Range: -6.3834
Max Act: 5.8834. Min Act: -0.1700
Data Index: 7738823 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3834. Min Range: -6.3834
Max Act: 5.8834. Min Act: -0.1700
Data Index: 5170923 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3834. Min Range: -6.3834
Max Act: 5.8834. Min Act: -0.1700
Data Index: 4312341 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3834. Min Range: -6.3834
Max Act: 5.8522. Min Act: -0.1700
Data Index: 3738463 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3834. Min Range: -6.3834
Max Act: 5.8522. Min Act: -0.1700
Data Index: 702432 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3834. Min Range: -6.3834
Max Act: 5.8209. Min Act: -0.1700
Data Index: 1591773 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3834. Min Range: -6.3834
Max Act: 5.8209. Min Act: -0.1700
Data Index: 8317638 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3834. Min Range: -6.3834
Max Act: 5.7897. Min Act: -0.1700
Data Index: 2108841 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3834. Min Range: -6.3834
Max Act: 5.7897. Min Act: -0.1700
Data Index: 1591774 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3834. Min Range: -6.3834
Max Act: 5.8209. Min Act: -0.1700
Data Index: 5272900 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3834. Min Range: -6.3834
Max Act: 5.7897. Min Act: -0.1700
Data Index: 2736925 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3834. Min Range: -6.3834
Max Act: 5.7584. Min Act: -0.1700
Data Index: 7059841 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3834. Min Range: -6.3834
Max Act: 5.7897. Min Act: -0.1700
Data Index: 4788343 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19