Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2916 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5708. Min Range: -6.5708
Max Act: 6.5708. Min Act: -0.1700
Data Index: 6278566 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5708. Min Range: -6.5708
Max Act: 6.1646. Min Act: -0.1700
Data Index: 6823878 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5708. Min Range: -6.5708
Max Act: 6.1021. Min Act: -0.1700
Data Index: 6712009 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5708. Min Range: -6.5708
Max Act: 6.0396. Min Act: -0.1700
Data Index: 782314 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5708. Min Range: -6.5708
Max Act: 5.9771. Min Act: -0.1700
Data Index: 3629953 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5708. Min Range: -6.5708
Max Act: 5.9771. Min Act: -0.1700
Data Index: 6777658 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5708. Min Range: -6.5708
Max Act: 5.9458. Min Act: -0.1700
Data Index: 6407207 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5708. Min Range: -6.5708
Max Act: 5.9458. Min Act: -0.1700
Data Index: 1314483 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5708. Min Range: -6.5708
Max Act: 5.9458. Min Act: -0.1700
Data Index: 8333635 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5708. Min Range: -6.5708
Max Act: 5.9146. Min Act: -0.1700
Data Index: 8664616 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5708. Min Range: -6.5708
Max Act: 5.9146. Min Act: -0.1700
Data Index: 7126100 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5708. Min Range: -6.5708
Max Act: 5.8833. Min Act: -0.1700
Data Index: 7896732 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5708. Min Range: -6.5708
Max Act: 5.9146. Min Act: -0.1700
Data Index: 4154286 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5708. Min Range: -6.5708
Max Act: 5.8833. Min Act: -0.1700
Data Index: 1977943 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5708. Min Range: -6.5708
Max Act: 5.8521. Min Act: -0.1700
Data Index: 3816021 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5708. Min Range: -6.5708
Max Act: 5.8521. Min Act: -0.1700
Data Index: 7938804 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5708. Min Range: -6.5708
Max Act: 5.8208. Min Act: -0.1700
Data Index: 6070844 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5708. Min Range: -6.5708
Max Act: 5.8208. Min Act: -0.1700
Data Index: 4192351 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5708. Min Range: -6.5708
Max Act: 5.8208. Min Act: -0.1700
Data Index: 1370259 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5708. Min Range: -6.5708
Max Act: 5.7896. Min Act: -0.1700
Data Index: 4501496 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19