Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2610 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3681. Min Range: -8.3681
Max Act: 8.3681. Min Act: -0.1700
Data Index: 2971467 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3681. Min Range: -8.3681
Max Act: 8.0556. Min Act: -0.1700
Data Index: 2784780 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3681. Min Range: -8.3681
Max Act: 7.8993. Min Act: -0.1700
Data Index: 9834 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3681. Min Range: -8.3681
Max Act: 7.8993. Min Act: -0.1700
Data Index: 317839 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3681. Min Range: -8.3681
Max Act: 7.8993. Min Act: -0.1700
Data Index: 3976079 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3681. Min Range: -8.3681
Max Act: 7.8056. Min Act: -0.1700
Data Index: 2279891 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3681. Min Range: -8.3681
Max Act: 7.8368. Min Act: -0.1700
Data Index: 1363011 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3681. Min Range: -8.3681
Max Act: 7.7743. Min Act: -0.1700
Data Index: 7211314 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3681. Min Range: -8.3681
Max Act: 7.7431. Min Act: -0.1700
Data Index: 4889392 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3681. Min Range: -8.3681
Max Act: 7.6806. Min Act: -0.1700
Data Index: 1415368 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3681. Min Range: -8.3681
Max Act: 7.6181. Min Act: -0.1700
Data Index: 4129372 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3681. Min Range: -8.3681
Max Act: 7.5868. Min Act: -0.1700
Data Index: 5506058 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3681. Min Range: -8.3681
Max Act: 7.4931. Min Act: -0.1700
Data Index: 4066054 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3681. Min Range: -8.3681
Max Act: 7.4618. Min Act: -0.1700
Data Index: 7373102 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3681. Min Range: -8.3681
Max Act: 7.3993. Min Act: -0.1700
Data Index: 6715116 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3681. Min Range: -8.3681
Max Act: 7.3681. Min Act: -0.1700
Data Index: 1989720 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3681. Min Range: -8.3681
Max Act: 7.3368. Min Act: -0.1700
Data Index: 4566357 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3681. Min Range: -8.3681
Max Act: 7.3368. Min Act: -0.1700
Data Index: 5522914 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3681. Min Range: -8.3681
Max Act: 7.3056. Min Act: -0.1700
Data Index: 4512037 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3681. Min Range: -8.3681
Max Act: 7.3056. Min Act: -0.1700
Data Index: 1174301 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19