Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1639 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9211. Min Range: -7.9211
Max Act: 7.9211. Min Act: -0.1700
Data Index: 3929313 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9211. Min Range: -7.9211
Max Act: 7.8586. Min Act: -0.1700
Data Index: 3532593 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9211. Min Range: -7.9211
Max Act: 7.8586. Min Act: -0.1700
Data Index: 4680670 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9211. Min Range: -7.9211
Max Act: 7.8586. Min Act: -0.1700
Data Index: 8125516 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9211. Min Range: -7.9211
Max Act: 7.8586. Min Act: -0.1700
Data Index: 3332441 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9211. Min Range: -7.9211
Max Act: 7.7961. Min Act: -0.1700
Data Index: 5978413 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9211. Min Range: -7.9211
Max Act: 7.7336. Min Act: -0.1700
Data Index: 2693530 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9211. Min Range: -7.9211
Max Act: 7.6711. Min Act: -0.1700
Data Index: 478858 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9211. Min Range: -7.9211
Max Act: 7.6711. Min Act: -0.1700
Data Index: 7016837 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9211. Min Range: -7.9211
Max Act: 7.5773. Min Act: -0.1700
Data Index: 3304628 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9211. Min Range: -7.9211
Max Act: 7.5148. Min Act: -0.1700
Data Index: 4255418 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9211. Min Range: -7.9211
Max Act: 7.5148. Min Act: -0.1700
Data Index: 7612107 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9211. Min Range: -7.9211
Max Act: 7.4523. Min Act: -0.1700
Data Index: 4477673 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9211. Min Range: -7.9211
Max Act: 7.3898. Min Act: -0.1700
Data Index: 1847400 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9211. Min Range: -7.9211
Max Act: 7.3898. Min Act: -0.1700
Data Index: 2286900 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9211. Min Range: -7.9211
Max Act: 7.3586. Min Act: -0.1700
Data Index: 4407996 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9211. Min Range: -7.9211
Max Act: 7.3586. Min Act: -0.1700
Data Index: 3692676 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9211. Min Range: -7.9211
Max Act: 7.3273. Min Act: -0.1700
Data Index: 3871702 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9211. Min Range: -7.9211
Max Act: 7.2961. Min Act: -0.1700
Data Index: 2568534 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9211. Min Range: -7.9211
Max Act: 7.2336. Min Act: -0.1700
Data Index: 5484922 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #19