Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1667 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1629. Min Range: -4.1629
Max Act: 4.1629. Min Act: -0.1700
Data Index: 4665658 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1629. Min Range: -4.1629
Max Act: 4.1004. Min Act: -0.1700
Data Index: 8430866 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1629. Min Range: -4.1629
Max Act: 4.0691. Min Act: -0.1700
Data Index: 1891369 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1629. Min Range: -4.1629
Max Act: 4.0691. Min Act: -0.1700
Data Index: 5177470 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1629. Min Range: -4.1629
Max Act: 4.1004. Min Act: -0.1700
Data Index: 6518081 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1629. Min Range: -4.1629
Max Act: 4.0379. Min Act: -0.1700
Data Index: 552208 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1629. Min Range: -4.1629
Max Act: 4.0379. Min Act: -0.1700
Data Index: 8612153 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1629. Min Range: -4.1629
Max Act: 4.0066. Min Act: -0.1700
Data Index: 3288256 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1629. Min Range: -4.1629
Max Act: 3.9754. Min Act: -0.1700
Data Index: 5562249 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1629. Min Range: -4.1629
Max Act: 4.0066. Min Act: -0.1700
Data Index: 1989281 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1629. Min Range: -4.1629
Max Act: 4.0066. Min Act: -0.1700
Data Index: 6897347 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1629. Min Range: -4.1629
Max Act: 4.0066. Min Act: -0.1700
Data Index: 1087071 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1629. Min Range: -4.1629
Max Act: 3.9754. Min Act: -0.1700
Data Index: 2610936 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1629. Min Range: -4.1629
Max Act: 3.9754. Min Act: -0.1700
Data Index: 2035235 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1629. Min Range: -4.1629
Max Act: 3.9441. Min Act: -0.1700
Data Index: 3843803 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1629. Min Range: -4.1629
Max Act: 3.9754. Min Act: -0.1700
Data Index: 7066397 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1629. Min Range: -4.1629
Max Act: 3.9441. Min Act: -0.1700
Data Index: 4902649 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1629. Min Range: -4.1629
Max Act: 3.9754. Min Act: -0.1700
Data Index: 2378502 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1629. Min Range: -4.1629
Max Act: 3.9441. Min Act: -0.1700
Data Index: 3697663 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1629. Min Range: -4.1629
Max Act: 3.9441. Min Act: -0.1700
Data Index: 5500971 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #19