Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2898 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8353. Min Range: -6.8353
Max Act: 6.8353. Min Act: -0.1700
Data Index: 4980978 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8353. Min Range: -6.8353
Max Act: 6.7416. Min Act: -0.1700
Data Index: 6504943 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8353. Min Range: -6.8353
Max Act: 6.6478. Min Act: -0.1700
Data Index: 1969012 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8353. Min Range: -6.8353
Max Act: 6.6478. Min Act: -0.1700
Data Index: 4028309 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8353. Min Range: -6.8353
Max Act: 6.5541. Min Act: -0.1700
Data Index: 124369 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8353. Min Range: -6.8353
Max Act: 6.4603. Min Act: -0.1700
Data Index: 6143570 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8353. Min Range: -6.8353
Max Act: 6.4603. Min Act: -0.1700
Data Index: 4262880 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8353. Min Range: -6.8353
Max Act: 6.4603. Min Act: -0.1700
Data Index: 2173820 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8353. Min Range: -6.8353
Max Act: 6.4603. Min Act: -0.1700
Data Index: 107592 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8353. Min Range: -6.8353
Max Act: 6.3978. Min Act: -0.1700
Data Index: 5126185 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8353. Min Range: -6.8353
Max Act: 6.3666. Min Act: -0.1700
Data Index: 2093987 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8353. Min Range: -6.8353
Max Act: 6.3353. Min Act: -0.1700
Data Index: 916569 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8353. Min Range: -6.8353
Max Act: 6.3353. Min Act: -0.1700
Data Index: 7693962 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8353. Min Range: -6.8353
Max Act: 6.3041. Min Act: -0.1700
Data Index: 645467 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8353. Min Range: -6.8353
Max Act: 6.3041. Min Act: -0.1700
Data Index: 1756258 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8353. Min Range: -6.8353
Max Act: 6.2728. Min Act: -0.1700
Data Index: 3397189 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8353. Min Range: -6.8353
Max Act: 6.2416. Min Act: -0.1700
Data Index: 362955 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8353. Min Range: -6.8353
Max Act: 6.2728. Min Act: -0.1700
Data Index: 3485934 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8353. Min Range: -6.8353
Max Act: 6.2103. Min Act: -0.1700
Data Index: 7955067 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8353. Min Range: -6.8353
Max Act: 6.2416. Min Act: -0.1700
Data Index: 1773265 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19