Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2643 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7869. Min Range: -5.7869
Max Act: 5.7869. Min Act: -0.1700
Data Index: 1743134 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7869. Min Range: -5.7869
Max Act: 5.7869. Min Act: -0.1700
Data Index: 4375063 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7869. Min Range: -5.7869
Max Act: 5.7557. Min Act: -0.1700
Data Index: 4210482 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7869. Min Range: -5.7869
Max Act: 5.7557. Min Act: -0.1700
Data Index: 6149789 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7869. Min Range: -5.7869
Max Act: 5.6619. Min Act: -0.1700
Data Index: 8794729 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7869. Min Range: -5.7869
Max Act: 5.6619. Min Act: -0.1700
Data Index: 7697424 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7869. Min Range: -5.7869
Max Act: 5.5682. Min Act: -0.1700
Data Index: 4333516 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7869. Min Range: -5.7869
Max Act: 5.5682. Min Act: -0.1700
Data Index: 1893977 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7869. Min Range: -5.7869
Max Act: 5.5057. Min Act: -0.1700
Data Index: 478855 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7869. Min Range: -5.7869
Max Act: 5.4744. Min Act: -0.1700
Data Index: 3546186 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7869. Min Range: -5.7869
Max Act: 5.5057. Min Act: -0.1700
Data Index: 4115003 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7869. Min Range: -5.7869
Max Act: 5.4432. Min Act: -0.1700
Data Index: 7540736 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7869. Min Range: -5.7869
Max Act: 5.4432. Min Act: -0.1700
Data Index: 6831345 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7869. Min Range: -5.7869
Max Act: 5.4432. Min Act: -0.1700
Data Index: 6843201 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7869. Min Range: -5.7869
Max Act: 5.4119. Min Act: -0.1700
Data Index: 5003854 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7869. Min Range: -5.7869
Max Act: 5.3807. Min Act: -0.1700
Data Index: 7947688 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7869. Min Range: -5.7869
Max Act: 5.3807. Min Act: -0.1700
Data Index: 3764298 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7869. Min Range: -5.7869
Max Act: 5.3807. Min Act: -0.1700
Data Index: 8457719 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7869. Min Range: -5.7869
Max Act: 5.3807. Min Act: -0.1700
Data Index: 3764423 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7869. Min Range: -5.7869
Max Act: 5.3494. Min Act: -0.1700
Data Index: 1259901 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19