Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 27 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7598. Min Range: -6.7598
Max Act: 6.7598. Min Act: -0.1700
Data Index: 932915 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7598. Min Range: -6.7598
Max Act: 6.4160. Min Act: -0.1700
Data Index: 3829071 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7598. Min Range: -6.7598
Max Act: 6.3848. Min Act: -0.1700
Data Index: 2167153 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7598. Min Range: -6.7598
Max Act: 6.3535. Min Act: -0.1700
Data Index: 8163494 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7598. Min Range: -6.7598
Max Act: 6.2910. Min Act: -0.1700
Data Index: 724096 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7598. Min Range: -6.7598
Max Act: 6.2910. Min Act: -0.1700
Data Index: 6612146 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7598. Min Range: -6.7598
Max Act: 6.2285. Min Act: -0.1700
Data Index: 1564525 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7598. Min Range: -6.7598
Max Act: 6.2285. Min Act: -0.1700
Data Index: 3596615 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7598. Min Range: -6.7598
Max Act: 6.1973. Min Act: -0.1700
Data Index: 33681 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7598. Min Range: -6.7598
Max Act: 6.1660. Min Act: -0.1700
Data Index: 8418907 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7598. Min Range: -6.7598
Max Act: 6.1035. Min Act: -0.1700
Data Index: 4773337 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7598. Min Range: -6.7598
Max Act: 6.1035. Min Act: -0.1700
Data Index: 5757276 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7598. Min Range: -6.7598
Max Act: 6.0723. Min Act: -0.1700
Data Index: 3304751 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7598. Min Range: -6.7598
Max Act: 6.0723. Min Act: -0.1700
Data Index: 5363791 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7598. Min Range: -6.7598
Max Act: 6.0723. Min Act: -0.1700
Data Index: 5305629 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7598. Min Range: -6.7598
Max Act: 6.0723. Min Act: -0.1700
Data Index: 6444544 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7598. Min Range: -6.7598
Max Act: 6.0098. Min Act: -0.1700
Data Index: 3542448 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7598. Min Range: -6.7598
Max Act: 6.0098. Min Act: -0.1700
Data Index: 1307630 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7598. Min Range: -6.7598
Max Act: 6.0098. Min Act: -0.1700
Data Index: 4600234 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7598. Min Range: -6.7598
Max Act: 5.9785. Min Act: -0.1700
Data Index: 714682 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19