Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2719 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.8629. Min Act: -0.1700
Data Index: 6658197 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.7692. Min Act: -0.1700
Data Index: 7707295 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.7379. Min Act: -0.1700
Data Index: 7510779 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.7379. Min Act: -0.1700
Data Index: 816591 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.7379. Min Act: -0.1700
Data Index: 6634329 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.7067. Min Act: -0.1700
Data Index: 2373047 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.6754. Min Act: -0.1700
Data Index: 4191148 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.6754. Min Act: -0.1700
Data Index: 8460688 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.6442. Min Act: -0.1700
Data Index: 3310291 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.6129. Min Act: -0.1700
Data Index: 6817572 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.6442. Min Act: -0.1700
Data Index: 1245722 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.6442. Min Act: -0.1700
Data Index: 1544210 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.6442. Min Act: -0.1700
Data Index: 3053752 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.6129. Min Act: -0.1700
Data Index: 5877424 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.6442. Min Act: -0.1700
Data Index: 863319 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.6442. Min Act: -0.1700
Data Index: 7537140 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.6754. Min Act: -0.1700
Data Index: 6878547 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.6442. Min Act: -0.1700
Data Index: 3992088 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.6129. Min Act: -0.1700
Data Index: 2910925 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8629. Min Range: -4.8629
Max Act: 4.6129. Min Act: -0.1700
Data Index: 3122693 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #19