Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1896 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4075. Min Range: -5.4075
Max Act: 5.4075. Min Act: -0.1700
Data Index: 3533252 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4075. Min Range: -5.4075
Max Act: 5.4075. Min Act: -0.1700
Data Index: 8680226 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4075. Min Range: -5.4075
Max Act: 5.3450. Min Act: -0.1700
Data Index: 3533250 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4075. Min Range: -5.4075
Max Act: 5.2825. Min Act: -0.1700
Data Index: 5349784 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4075. Min Range: -5.4075
Max Act: 5.2200. Min Act: -0.1700
Data Index: 5661257 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4075. Min Range: -5.4075
Max Act: 5.1263. Min Act: -0.1700
Data Index: 6950722 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4075. Min Range: -5.4075
Max Act: 5.0950. Min Act: -0.1700
Data Index: 7151131 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4075. Min Range: -5.4075
Max Act: 5.0950. Min Act: -0.1700
Data Index: 920879 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4075. Min Range: -5.4075
Max Act: 5.0638. Min Act: -0.1700
Data Index: 3533251 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4075. Min Range: -5.4075
Max Act: 5.0638. Min Act: -0.1700
Data Index: 5532102 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4075. Min Range: -5.4075
Max Act: 5.0638. Min Act: -0.1700
Data Index: 1061573 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4075. Min Range: -5.4075
Max Act: 5.0638. Min Act: -0.1700
Data Index: 7501988 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4075. Min Range: -5.4075
Max Act: 5.0638. Min Act: -0.1700
Data Index: 7348099 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4075. Min Range: -5.4075
Max Act: 5.0325. Min Act: -0.1700
Data Index: 311569 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4075. Min Range: -5.4075
Max Act: 5.0013. Min Act: -0.1700
Data Index: 4701008 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4075. Min Range: -5.4075
Max Act: 5.0325. Min Act: -0.1700
Data Index: 6486741 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4075. Min Range: -5.4075
Max Act: 5.0325. Min Act: -0.1700
Data Index: 6899194 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4075. Min Range: -5.4075
Max Act: 5.0013. Min Act: -0.1700
Data Index: 634547 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4075. Min Range: -5.4075
Max Act: 5.0013. Min Act: -0.1700
Data Index: 3803080 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4075. Min Range: -5.4075
Max Act: 5.0013. Min Act: -0.1700
Data Index: 8653710 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #19